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

    Neuronpedia

    INDEX
    Explanations

    instances of self-harm and methods of suicide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JvmStatic
    -0.41
     Aufbau
    -0.35
    AppMethodBeat
    -0.34
     Stell
    -0.34
    BSITE
    -0.33
    Kenn
    -0.33
    ętr
    -0.33
    EDEFAULT
    -0.33
    Breite
    -0.33
     Brix
    -0.33
    POSITIVE LOGITS
     automatiques
    0.71
     automatico
    0.66
    basicConfig
    0.65
     automatisch
    0.65
     unintentionally
    0.63
     automaticamente
    0.61
     automatically
    0.60
     automático
    0.60
     automatiquement
    0.59
     automatique
    0.59
    Act Density 1.076%

    No Known Activations