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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional responses or strong sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greateſt
    -0.62
     Weich
    -0.61
    ziasztok
    -0.59
     Correspond
    -0.58
     tayo
    -0.57
     ſame
    -0.56
    ſelf
    -0.56
    ſelves
    -0.55
     Windy
    -0.55
     Frequent
    -0.54
    POSITIVE LOGITS
     myself
    0.83
    DoubleQuotes
    0.80
    myself
    0.61
     personally
    0.61
     personalmente
    0.59
     recomiendo
    0.57
     admire
    0.56
     recomendo
    0.56
    個人的には
    0.55
     StatelessWidget
    0.55
    Act Density 0.426%

    No Known Activations