Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a negative outlook or concern about the state of the world

    oai_token-act-pair · gpt-3.5-turbo

    expressions that reflect negative perceptions or critiques of the world

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.83
    ricular
    -0.73
    rouse
    -0.71
    SpaceEngineers
    -0.68
    pez
    -0.67
    itone
    -0.66
    anches
    -0.65
    oyal
    -0.65
    */(
    -0.65
    effective
    -0.63
    POSITIVE LOGITS
     divided
    0.75
     fragmented
    0.72
     itself
    0.72
     darkened
    0.70
     Manifest
    0.67
     trillions
    0.66
     seeded
    0.64
     polarized
    0.64
     saturated
    0.63
     stagn
    0.63
    Act Density 0.783%

    No Known Activations