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

    Neuronpedia

    INDEX
    Explanations

    quotations or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    reported speech or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Klux
    -0.75
    Republican
    -0.71
    DonaldTrump
    -0.70
    Attorney
    -0.65
     mathemat
    -0.64
    Nor
    -0.62
    ocide
    -0.62
     barred
    -0.62
     impe
    -0.61
     punish
    -0.61
    POSITIVE LOGITS
    :"
    1.20
     "[
    0.89
    :[
    0.85
     goodbye
    0.84
     "âĢ¦
    0.83
    :
    0.80
     "...
    0.80
     ""
    0.79
     "(
    0.78
     hello
    0.74
    Act Density 0.200%

    No Known Activations