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

    Neuronpedia

    INDEX
    Explanations

    conversations focused on decision-making and assessing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ower
    -0.18
    umu
    -0.17
    ÄĽ
    -0.14
    wig
    -0.14
    αι
    -0.14
    585
    -0.14
    /***/
    -0.14
    aira
    -0.13
    ãģĭãģ®
    -0.13
    IMUM
    -0.13
    POSITIVE LOGITS
    eyi
    0.16
    ÙĪارÙĩ
    0.15
     unarmed
    0.15
    rase
    0.15
    Disposition
    0.15
    jte
    0.14
    balls
    0.14
    bedo
    0.14
    edo
    0.13
    braco
    0.13
    Act Density 0.397%

    No Known Activations