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

    Neuronpedia

    INDEX
    Explanations

    expressions of approval or positive assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqlSession
    -0.64
    ($__
    -0.61
    ;++
    -0.58
     />';
    -0.56
     piú
    -0.56
    räck
    -0.56
     fraî
    -0.56
    __":
    -0.55
    ----</
    -0.55
     pareti
    -0.54
    POSITIVE LOGITS
    GEBURTSDATUM
    0.69
    ftagPool
    0.68
     مشين
    0.60
    UrlResolution
    0.60
    +#+#
    0.59
    adə
    0.56
    зулта
    0.55
    Diweddarwch
    0.53
     sekali
    0.53
    Datuak
    0.52
    Act Density 0.187%

    No Known Activations