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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal impact or experience related to societal issues

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

    impact or affect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idi
    -0.31
     spit
    -0.29
    classnames
    -0.28
     kla
    -0.28
     honors
    -0.28
    ESC
    -0.28
     gave
    -0.26
     onCreateView
    -0.26
     super
    -0.25
     performed
    -0.25
    POSITIVE LOGITS
     impact
    1.05
     affect
    1.02
    impact
    0.98
     affects
    0.98
    Impact
    0.97
     affected
    0.96
     Impact
    0.95
     impacts
    0.95
     Affected
    0.95
    affect
    0.95
    Act Density 0.111%

    No Known Activations