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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating the ability to perform an action or the impossibility of an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing limitations or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rongh
    -0.62
     assorted
    -0.60
    leted
    -0.58
    ghan
    -0.58
     mull
    -0.57
     rather
    -0.56
    rather
    -0.56
     unsurprisingly
    -0.56
    ischer
    -0.55
    JO
    -0.54
    POSITIVE LOGITS
     anymore
    1.39
     nor
    1.06
     unless
    0.89
     anything
    0.88
    urate
    0.85
     adequately
    0.85
     anywhere
    0.79
     anybody
    0.79
     coherent
    0.78
     satisf
    0.78
    Act Density 0.352%

    No Known Activations