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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms that specify examples or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.83
     purpoſe
    -0.81
     greateſt
    -0.75
     Diſ
    -0.73
     ſeveral
    -0.73
     doInBackground
    -0.71
     itſelf
    -0.70
     raiſ
    -0.70
     fubject
    -0.69
     ſub
    -0.69
    POSITIVE LOGITS
     like
    0.88
    比如
    0.86
     bijvoorbeeld
    0.83
     esimerkiksi
    0.81
     zoals
    0.80
     Like
    0.80
    例えば
    0.79
    voorbeeld
    0.79
     например
    0.78
    例如
    0.78
    Act Density 0.236%

    No Known Activations