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

    Neuronpedia

    INDEX
    Explanations

    references to conditional and potential outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ¬
    -0.15
    vero
    -0.15
    вий
    -0.14
    ataire
    -0.14
    _popup
    -0.14
    entine
    -0.14
    ierz
    -0.14
    vÄĽd
    -0.13
    ussen
    -0.13
    ellen
    -0.13
    POSITIVE LOGITS
     volont
    0.20
     voluntary
    0.19
     demand
    0.19
     volunt
    0.17
     Demand
    0.17
    edik
    0.16
     SEND
    0.15
    _demand
    0.15
    optional
    0.15
     willing
    0.14
    Act Density 0.011%

    No Known Activations