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

    Neuronpedia

    INDEX
    Explanations

    dates and events in chronological order

    oai_token-act-pair · gpt-3.5-turbo

    temporal references and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pac
    -0.70
    Ķ
    -0.69
    enz
    -0.63
    oya
    -0.62
    BD
    -0.61
    Detailed
    -0.60
    ono
    -0.60
    atan
    -0.59
    ²¾
    -0.59
    Optional
    -0.59
    POSITIVE LOGITS
     it
    0.99
     they
    0.88
     he
    0.86
     there
    0.86
     nobody
    0.82
     pundits
    0.77
     she
    0.76
     however
    0.74
     we
    0.72
     detractors
    0.71
    Act Density 0.220%

    No Known Activations