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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical outcomes and patient satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    interventions or loosening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.34
    AttributeSet
    -0.33
    帖最后由
    -0.32
     glove
    -0.32
     rental
    -0.30
    ionato
    -0.30
     round
    -0.30
    InteropServices
    -0.30
     comparison
    -0.29
     transitioning
    -0.29
    POSITIVE LOGITS
    SequentialGroup
    0.85
    
    0.63
    RenderAtEndOf
    0.55
     cellspacing
    0.52
     Италијани
    0.52
     simplifié
    0.50
    醐
    0.49
     surla
    0.49
    CrossRef
    0.48
    뀜
    0.47
    Act Density 0.079%

    No Known Activations