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

    Neuronpedia

    INDEX
    Explanations

    commands related to enabling or disabling features and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.68
    DockStyle
    -0.63
    indrome
    -0.62
     spéciales
    -0.60
    GEBURTSDATUM
    -0.60
     שוליים
    -0.60
     réguli
    -0.59
    ьаж
    -0.59
     anzub
    -0.59
    posedge
    -0.58
    POSITIVE LOGITS
    disable
    0.82
     Fatigue
    0.81
     fatigue
    0.79
    fatigue
    0.75
     disable
    0.72
     Difficulties
    0.68
    Fatigue
    0.67
     Вікі
    0.65
    Disable
    0.64
     difficulties
    0.62
    Act Density 0.112%

    No Known Activations