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

    Neuronpedia

    INDEX
    Explanations

    negations and their variations in tense

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.83
    o
    -0.81
    ing
    -0.75
    .
    -0.70
    e
    -0.64
    i
    -0.62
    5
    -0.61
    a
    -0.61
     The
    -0.60
     A
    -0.60
    POSITIVE LOGITS
     متعلقه
    1.40
    expandindo
    1.38
     مشين
    1.33
     للمعارف
    1.26
    $.
    1.23
    原始内容存档于
    1.19
    IsMutable
    1.17
    NUMX
    1.15
    ".
    1.15
     Efq
    1.15
    Act Density 0.012%

    No Known Activations