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

    Neuronpedia

    INDEX
    Explanations

    references to criticisms and analyses of societal or legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.66
    RenderAtEndOf
    -0.61
    ########.
    -0.61
    ValueGenerated
    -0.54
    Erreferentziak
    -0.53
     suyo
    -0.53
     ModelExpression
    -0.53
     surla
    -0.52
    
    -0.52
     فريبيس
    -0.52
    POSITIVE LOGITS
    UVWXYZ
    0.57
     ivelany
    0.55
    CompleteListener
    0.54
    UnknownFields
    0.53
     arşivlendi
    0.53
    pense
    0.52
    adpleegd
    0.51
    例句
    0.51
     ISA
    0.50
     Synthesis
    0.49
    Act Density 1.148%

    No Known Activations