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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (__('
    -0.59
     Fen
    -0.58
    zige
    -0.57
    telefono
    -0.56
    舅
    -0.54
     Hag
    -0.54
    ajaan
    -0.53
     Potter
    -0.53
    rome
    -0.52
    ดย
    -0.52
    POSITIVE LOGITS
    __":
    1.23
    principalTable
    1.18
     Roskov
    1.14
    __':
    1.06
    oredCriteria
    1.04
    findpost
    1.00
    tagHelperRunner
    0.99
     الاطلاع
    0.96
    تقاوى
    0.95
    __":
    0.93
    Act Density 0.204%

    No Known Activations