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

    Neuronpedia

    INDEX
    Explanations

    code structure elements and references to programming constructs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Formal
    -0.50
    Formal
    -0.46
    ++)
    -0.45
     formal
    -0.44
     vriend
    -0.44
     Mar
    -0.42
    dar
    -0.42
    /
    -0.42
     
    -0.41
     Bennet
    -0.41
    POSITIVE LOGITS
    :✨
    0.94
    Chham
    0.81
     فريبيس
    0.79
     ddelweddau
    0.78
    abestanden
    0.74
    Viitteet
    0.74
    存于互联网档案馆
    0.73
     itſelf
    0.73
    localctx
    0.73
     мәкал
    0.73
    Act Density 0.009%

    No Known Activations