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

    Neuronpedia

    INDEX
    Explanations

    key decision-making words and phrases indicative of personal agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.65
     kaarangay
    -0.51
    AutoScaleMode
    -0.50
    StructEnd
    -0.48
     ویکی‌پدی
    -0.47
     nawr
    -0.47
     Signalez
    -0.46
     Wicidata
    -0.46
     utafitiHapana
    -0.46
    
    -0.45
    POSITIVE LOGITS
     must
    2.81
    must
    2.39
    Must
    2.25
     Must
    2.22
     need
    2.17
     MUST
    2.00
    ต้อง
    1.98
     phải
    1.95
    必须
    1.94
     måste
    1.93
    Act Density 2.862%

    No Known Activations