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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific metrics related to performance evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _PRIV
    -0.17
     رسÙħ
    -0.17
    roman
    -0.16
    andering
    -0.16
    Ïģιο
    -0.15
    ALCHEMY
    -0.15
    ekk
    -0.15
    liche
    -0.14
    eterangan
    -0.14
    uin
    -0.14
    POSITIVE LOGITS
    oux
    0.14
    ifr
    0.14
     Duck
    0.14
    oni
    0.14
     Ware
    0.14
    onium
    0.14
     Herr
    0.13
    placer
    0.13
    éIJĺ
    0.13
    etry
    0.13
    Act Density 7.712%

    No Known Activations