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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of enrollment and enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ionic
    -0.16
     Enforcement
    -0.15
    pering
    -0.15
    ortic
    -0.15
    boards
    -0.15
    inherits
    -0.15
    دÙĨ
    -0.14
    cuts
    -0.14
    tram
    -0.14
    uteur
    -0.14
    POSITIVE LOGITS
    ments
    0.26
    /disable
    0.25
    ment
    0.25
    igma
    0.18
    MENT
    0.18
    -disable
    0.18
    ables
    0.17
    GLISH
    0.17
    IRONMENT
    0.17
    hardt
    0.17
    Act Density 0.091%

    No Known Activations