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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and emphatic statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.16
     доÑģ
    -0.14
    ocado
    -0.14
    reature
    -0.14
    roperty
    -0.14
    inz
    -0.13
    achi
    -0.13
    емаÑĤи
    -0.13
    orado
    -0.13
    urette
    -0.13
    POSITIVE LOGITS
     have
    0.16
    rollo
    0.15
    itals
    0.14
    've
    0.14
    ancock
    0.14
    atan
    0.14
    elong
    0.14
     tôn
    0.13
    ips
    0.13
    cps
    0.13
    Act Density 0.102%

    No Known Activations