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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a willingness to act or agree

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

    "Willing to" or readiness to act

    np_acts-logits-general · gemini-2.0-flash

    willingness to agree or do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.84
    IndentedString
    -0.84
    TypedDataSet
    -0.83
     ModelExpression
    -0.81
    出版年
    -0.80
    SharedDtor
    -0.77
    verwijspagina
    -0.69
    AutoScaleMode
    -0.69
    rrggbb
    -0.68
    "]);
    -0.67
    POSITIVE LOGITS
     accept
    0.82
    accept
    0.70
     sacrifice
    0.70
     cooperate
    0.68
     accepting
    0.64
     cooperation
    0.63
     budge
    0.63
     sacrifices
    0.63
     sacrific
    0.63
     accepts
    0.60
    Act Density 0.141%

    No Known Activations