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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activity and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     démoc
    -0.48
    is
    -0.47
     planas
    -0.47
     is
    -0.46
    ↵↵
    -0.46
     Preußen
    -0.45
    alibaba
    -0.45
     AssemblyCulture
    -0.45
     avantages
    -0.45
     crede
    -0.45
    POSITIVE LOGITS
     nahilalakip
    1.06
    WaitGroup
    0.99
     intptr
    0.94
     betweenstory
    0.92
     ModelExpression
    0.88
    Vidite
    0.85
     ujednoznacz
    0.81
     noqa
    0.80
     esternos
    0.78
    GraphicsUnit
    0.76
    Act Density 0.653%

    No Known Activations