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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with tension and human conflict

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

    following conjunctions

    np_acts-logits-general · gemini-2.0-flash

    but contrasted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     troubles
    -0.55
    trouble
    -0.54
    classnames
    -0.53
    disaster
    -0.50
     trouble
    -0.50
     cytotoxic
    -0.49
    Risks
    -0.49
    risk
    -0.48
    error
    -0.48
     riesgo
    -0.47
    POSITIVE LOGITS
    TypedDataSet
    0.66
    forName
    0.64
    ThroughAttribute
    0.64
    RenderAtEndOf
    0.64
    InjectAttribute
    0.62
     rewarding
    0.61
    HasAnnotation
    0.60
     <=",
    0.59
    enderror
    0.58
     चीज़ों
    0.57
    Act Density 0.492%

    No Known Activations