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

    Neuronpedia

    INDEX
    Explanations

    JavaScript push() method being called

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "push" and its variations, indicating contexts of encouragement or advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abol
    -0.80
    BuyableInstoreAndOnline
    -0.77
    omial
    -0.69
    redited
    -0.68
     Recogn
    -0.67
    ufact
    -0.65
     poss
    -0.64
     Surviv
    -0.63
     Distribut
    -0.63
     Surv
    -0.62
    POSITIVE LOGITS
    push
    0.90
     push
    0.88
    back
    0.88
    arte
    0.85
    ups
    0.85
    overs
    0.83
    pa
    0.81
    chairs
    0.81
     pushing
    0.79
    iment
    0.78
    Act Density 0.014%

    No Known Activations