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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific years or numerical references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    774
    -0.15
    lem
    -0.14
     ItemType
    -0.14
    íĸī
    -0.14
    Ìĥ
    -0.14
     STATES
    -0.14
     deep
    -0.13
    erli
    -0.13
    rina
    -0.13
    Å¡ov
    -0.13
    POSITIVE LOGITS
    asse
    0.16
    mada
    0.16
    iner
    0.15
    indy
    0.15
    enu
    0.15
     season
    0.14
    ulis
    0.14
    azu
    0.14
    asn
    0.14
    efa
    0.14
    Act Density 0.062%

    No Known Activations