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

    Neuronpedia

    INDEX
    Explanations

    colons followed by phrases indicating lists or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IFORNIA
    -0.80
    mybatisplus
    -0.73
    VIRONMENT
    -0.71
    BRARY
    -0.70
    Dziękuję
    -0.69
     Efq
    -0.69
    ſhip
    -0.69
     TAMBIÉN
    -0.67
    ADIAN
    -0.67
    ślę
    -0.67
    POSITIVE LOGITS
    ":
    0.79
    <bos>
    0.74
    ):
    0.72
    !):
    0.71
    ".
    0.68
    "[
    0.68
    ";
    0.67
    ”:
    0.67
    ))){
    0.67
    "):
    0.66
    Act Density 0.251%

    No Known Activations