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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.84
     snippetHide
    -0.83
    rungsseite
    -0.81
     myſelf
    -0.81
     itſelf
    -0.81
     auffi
    -0.81
     $_"
    -0.80
     Theſe
    -0.79
     ")");
    -0.77
     raiſ
    -0.77
    POSITIVE LOGITS
    moni
    0.47
     рез
    0.41
    biotics
    0.40
    ,
    0.39
    Uwagi
    0.37
     stay
    0.35
    jdt
    0.35
    AutoScale
    0.34
     Sam
    0.34
    йом
    0.34
    Act Density 0.033%

    No Known Activations