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

    Neuronpedia

    INDEX
    Explanations

    instances of inequality or negation in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     samband
    -0.60
    feren
    -0.58
    чик
    -0.55
    ———-
    -0.53
    ERING
    -0.53
    newBuilder
    -0.53
    urlpatterns
    -0.52
    jenie
    -0.52
     الاطلاع
    -0.50
    glMatrixMode
    -0.50
    POSITIVE LOGITS
    EDEFAULT
    0.91
    null
    0.85
     žiad
    0.75
     Normdatei
    0.73
     contextLoads
    0.71
     poffible
    0.71
     itſelf
    0.71
    DECREF
    0.71
     YET
    0.70
    archiviato
    0.70
    Act Density 0.022%

    No Known Activations