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

    Neuronpedia

    INDEX
    Explanations

    names or terms mentioned as the subject of discussion or investigation

    oai_token-act-pair · gpt-3.5-turbo

    references to specific inquiries or topics being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azon
    -0.82
    rid
    -0.76
    atever
    -0.74
    ahime
    -0.73
    lez
    -0.72
     millenn
    -0.72
     newcom
    -0.70
    ERAL
    -0.69
    urate
    -0.69
    inders
    -0.68
    POSITIVE LOGITS
    */(
    0.83
    :(
    0.67
     belonged
    0.65
    hess
    0.63
    oux
    0.59
     belong
    0.58
    âĸĵ
    0.57
     belongs
    0.56
    abwe
    0.55
    ube
    0.54
    Act Density 0.103%

    No Known Activations