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

    Neuronpedia

    INDEX
    Explanations

    references to protests, demonstrations, and related actions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.63
    BASEPATH
    -0.60
    ModelSerializer
    -0.59
     Italijanski
    -0.59
    writeField
    -0.56
    UnsafeEnabled
    -0.54
    Glück
    -0.53
    DoubleQuotes
    -0.52
     Pristupljeno
    -0.52
    agaimana
    -0.51
    POSITIVE LOGITS
     protesters
    1.52
     protests
    1.49
     protest
    1.44
     protestors
    1.41
     Protest
    1.41
     protester
    1.38
     demonstrators
    1.35
     protesting
    1.29
    protest
    1.29
     protes
    1.22
    Act Density 0.187%

    No Known Activations