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

    Neuronpedia

    INDEX
    Explanations

    words or characters from non-English languages and scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    out
    -0.49
    non
    -0.45
    in
    -0.45
    te
    -0.44
    over
    -0.43
    ["
    -0.43
    chen
    -0.43
    出
    -0.43
     für
    -0.42
    set
    -0.41
    POSITIVE LOGITS
     Efq
    1.05
     Anſ
    0.96
     Мексичка
    0.94
    ՚
    0.92
     myſelf
    0.83
     Majefty
    0.82
    .}~\
    0.82
    usermodel
    0.80
     تانيه
    0.80
    endaftaran
    0.80
    Act Density 0.018%

    No Known Activations