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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and waiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.71
    Gambas
    -0.63
    ArgsConstructor
    -0.60
    billon
    -0.58
     defaultstate
    -0.56
    Résultats
    -0.56
    APORE
    -0.55
     ✭✭
    -0.53
     Indah
    -0.53
    AutoScale
    -0.53
    POSITIVE LOGITS
     STOP
    0.73
    STOP
    0.71
     stop
    0.67
     detener
    0.65
     stopping
    0.63
    навли
    0.63
    stop
    0.62
    Stop
    0.62
    IntoConstraints
    0.61
    Stopping
    0.61
    Act Density 0.250%

    No Known Activations