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

    Neuronpedia

    INDEX
    Explanations

    phrases involving statements of belief or debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]")]
    -0.74
    onAttach
    -0.73
     المعيارى
    -0.66
    UIControlState
    -0.59
     surla
    -0.58
     TextInputType
    -0.57
    ActionCreators
    -0.56
     незавершена
    -0.56
    Xna
    -0.56
    المناصب
    -0.55
    POSITIVE LOGITS
     reasoning
    0.71
     reason
    0.71
    reason
    0.67
     Explanation
    0.63
     explanation
    0.63
    理由
    0.60
     Rationale
    0.60
    Reason
    0.59
     Reason
    0.58
     Reasoning
    0.58
    Act Density 0.208%

    No Known Activations