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

    Neuronpedia

    INDEX
    Explanations

    general expressions of intent or action

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

    "[verb] so" construction

    np_acts-logits-general · gemini-2.0-flash

    do so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.70
     NSCoder
    -0.69
    InjectAttribute
    -0.69
    +#+#
    -0.69
    LookAnd
    -0.67
     Theſe
    -0.67
    
    -0.65
    ModelSerializer
    -0.65
    -0.63
     unknownFields
    -0.63
    POSITIVE LOGITS
     so
    4.01
    so
    2.91
    So
    2.51
     So
    2.40
     так
    2.04
     så
    2.00
     così
    1.86
     SO
    1.85
    如此
    1.63
     כך
    1.57
    Act Density 0.492%

    No Known Activations