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

    Neuronpedia

    INDEX
    Explanations

    elements of structured data related to indices and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.63
    ↵↵
    -0.57
     '
    -0.53
     "
    -0.51
    ppelin
    -0.49
     Z
    -0.49
    LookAnd
    -0.48
     The
    -0.47
     K
    -0.47
     ‘
    -0.46
    POSITIVE LOGITS
    VersionUID
    0.92
     समीक्षक
    0.88
    DataAnnotations
    0.83
     pleaſure
    0.82
    原始内容存档于
    0.78
    KommentareTeilen
    0.78
    Referències
    0.77
     arxiv
    0.75
     itſelf
    0.75
    CloseOperation
    0.74
    Act Density 0.365%

    No Known Activations