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

    Neuronpedia

    INDEX
    Explanations

    conditional and hypothetical statements related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rang
    -0.17
    ilor
    -0.16
    orate
    -0.15
    .pretty
    -0.15
    stor
    -0.15
    accion
    -0.14
    este
    -0.14
    alone
    -0.14
     bid
    -0.14
     nors
    -0.14
    POSITIVE LOGITS
     maur
    0.15
    ocket
    0.15
    éĩı
    0.15
     irr
    0.13
    unny
    0.13
    erli
    0.13
    isu
    0.13
    odesk
    0.13
    indo
    0.13
     foregoing
    0.13
    Act Density 0.093%

    No Known Activations