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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    caret symbols or related special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.70
     seiz
    -0.69
    ividual
    -0.68
    itia
    -0.67
     Samar
    -0.66
     Ital
    -0.63
    ensical
    -0.62
    icio
    -0.62
    oran
    -0.62
     ANGEL
    -0.61
    POSITIVE LOGITS
    Ni
    0.83
    graph
    0.82
    plane
    0.81
    {\
    0.81
    -+
    0.78
    workshop
    0.77
    ¯
    0.77
    href
    0.77
    planes
    0.76
    ł
    0.75
    Act Density 0.015%

    No Known Activations