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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions and effects related to health and well-being

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

    on, for, or to a subject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.74
    ViewInit
    -0.71
     CURIAM
    -0.67
     CommonModule
    -0.66
     pleaſure
    -0.66
     الحره
    -0.65
     FetchType
    -0.65
    matchCondition
    -0.63
     beſ
    -0.62
     ſtill
    -0.62
    POSITIVE LOGITS
    对
    0.47
    这对
    0.46
    health
    0.45
     health
    0.43
     detrimental
    0.42
     impact
    0.40
    對
    0.39
     harming
    0.38
     Impact
    0.38
     对
    0.37
    Act Density 0.209%

    No Known Activations