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

    Neuronpedia

    INDEX
    Explanations

    numbers or numeric patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.91
    TagMode
    -0.88
    AddTagHelper
    -0.88
    IsMutable
    -0.82
    majánló
    -0.79
     Савезне
    -0.77
     ब्रेकडाउन
    -0.77
    tagHelperRunner
    -0.76
     OMITBAD
    -0.75
     Comprometido
    -0.75
    POSITIVE LOGITS
    x
    1.06
     x
    0.71
    X
    0.60
    ://
    0.51
    <td>
    0.49
    х
    0.48
     X
    0.47
    M
    0.46
    <strong>
    0.46
    _
    0.42
    Act Density 0.336%

    No Known Activations