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

    Neuronpedia

    INDEX
    Explanations

    statements about goals or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fron
    -0.15
    ноп
    -0.14
    ewood
    -0.14
    ÑģÑĤÑĢа
    -0.14
    astle
    -0.14
    tul
    -0.14
    aks
    -0.13
    lesi
    -0.13
    éĢĨ
    -0.13
     clar
    -0.13
    POSITIVE LOGITS
     to
    0.17
    togroup
    0.16
    ToFit
    0.16
     ÑĩÑĤобÑĭ
    0.15
    _Helper
    0.14
    öz
    0.14
    anio
    0.14
     actionTypes
    0.14
     Nich
    0.14
    ityEngine
    0.14
    Act Density 0.037%

    No Known Activations