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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.77
    AutoScaleMode
    -0.69
    blende
    -0.63
    出版年
    -0.61
     Tant
    -0.57
    ticulture
    -0.55
     gelang
    -0.54
    وئ
    -0.53
     Bite
    -0.49
     Edible
    -0.49
    POSITIVE LOGITS
     فريبيس
    0.78
    Šaltiniai
    0.63
     lenker
    0.62
    InjectMocks
    0.59
    expandindo
    0.57
     خارجية
    0.56
     transfieras
    0.56
     <<<<<<<<<<<<<<
    0.56
     iprot
    0.55
     can
    0.54
    Act Density 0.025%

    No Known Activations