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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases about taking action or making plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquement
    -0.15
    hc
    -0.15
    etro
    -0.15
    ĴĮ
    -0.14
     rencont
    -0.14
    ì¦Ŀ
    -0.14
    ète
    -0.14
    éijij
    -0.14
    ìĺ¥
    -0.14
    aku
    -0.14
    POSITIVE LOGITS
     Pros
    0.16
    á»ĭch
    0.16
     pros
    0.15
    Pros
    0.15
    veau
    0.14
    /***/
    0.14
    egade
    0.14
    tha
    0.14
    ingleton
    0.14
    pawn
    0.14
    Act Density 0.203%

    No Known Activations