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

    Neuronpedia

    INDEX
    Explanations

    references to legal concerns or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.75
     ExecuteAsync
    -0.74
    saraba
    -0.74
     ProtoMessage
    -0.72
    Билгалдахарш
    -0.69
     fascism
    -0.69
     compactness
    -0.69
     contextLoads
    -0.66
     uParam
    -0.66
    IsContent
    -0.66
    POSITIVE LOGITS
     quite
    0.87
     rather
    0.76
     concerning
    0.75
     Quite
    0.66
    rather
    0.63
    quite
    0.63
    Quite
    0.62
    phazard
    0.58
    Rather
    0.58
     Rather
    0.58
    Act Density 0.316%

    No Known Activations