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

    Neuronpedia

    INDEX
    Explanations

    verbs related to influence, initiative, and movement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to motivation or actions that lead to outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.97
    çĦ
    -0.77
    ereo
    -0.75
    roma
    -0.74
    aido
    -0.71
    osuke
    -0.68
     Anniversary
    -0.68
     Sud
    -0.68
     Lumpur
    -0.68
    iannopoulos
    -0.66
    POSITIVE LOGITS
     driving
    0.90
    driving
    0.76
     away
    0.75
    bike
    0.73
    wheel
    0.71
     wedge
    0.71
    bys
    0.70
    ousel
    0.69
    iday
    0.69
     hunger
    0.67
    Act Density 0.027%

    No Known Activations