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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical relationships and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iNdEx
    -0.62
     unknownFields
    -0.61
    Oneof
    -0.55
    specialchars
    -0.52
    archiviato
    -0.52
     Вікі
    -0.52
    OrWhiteSpace
    -0.51
     NotImplemented
    -0.51
    ctrica
    -0.51
    ╝
    -0.49
    POSITIVE LOGITS
     two
    0.54
     صوتيه
    0.54
    two
    0.54
    AutoField
    0.53
     termica
    0.51
     ambas
    0.51
     between
    0.51
     betweenstory
    0.51
     beide
    0.50
    两者
    0.50
    Act Density 0.591%

    No Known Activations