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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical data and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.50
    ,
    -0.49
    着
    -0.49
    feinander
    -0.49
    '
    -0.48
    <eos>
    -0.43
    /*
    -0.43
    ↵
    -0.42
    <0xE6>
    -0.42
     образом
    -0.41
    POSITIVE LOGITS
     للمعارف
    0.98
     يتيمه
    0.94
    ](#
    0.91
    出版年
    0.89
    MigrationBuilder
    0.89
    atsby
    0.89
    Халык
    0.86
    *-*-
    0.84
    Portale
    0.82
    Portail
    0.80
    Act Density 0.419%

    No Known Activations