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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or consent

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

    agreeing to actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EXC
    -0.34
     revital
    -0.34
    throw
    -0.33
     traditionally
    -0.33
    ReferenceEquals
    -0.31
    addis
    -0.31
    uktur
    -0.31
     اح
    -0.31
     last
    -0.31
    IBOutlet
    -0.31
    POSITIVE LOGITS
     agreeing
    0.95
    同意
    0.94
     Agree
    0.93
     agree
    0.93
    agree
    0.90
    Agree
    0.89
     consenting
    0.88
     agrees
    0.87
     согласи
    0.87
     agreement
    0.83
    Act Density 0.038%

    No Known Activations