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

    Neuronpedia

    INDEX
    Explanations

    references to scientific figures or data points within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.90
    MENAFN
    -0.88
     Houſe
    -0.83
     houſe
    -0.80
     ་་
    -0.78
     purpoſe
    -0.78
     disponibilités
    -0.77
     ―――――
    -0.75
     ſeveral
    -0.75
    ſelf
    -0.71
    POSITIVE LOGITS
    see
    0.65
    ie
    0.54
    例えば
    0.52
    .
    0.51
    i
    0.50
    Table
    0.49
    ex
    0.49
     «
    0.48
    as
    0.47
    See
    0.46
    Act Density 0.757%

    No Known Activations