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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressions related to incrementing or modifying numerical values in code.

    oai_token-act-pair · gpt-4oTriggered by @pigeonzow
    New Auto-Interp
    Negative Logits
    -
    -0.83
    '
    -0.72
     I
    -0.68
    ’
    -0.68
     H
    -0.65
    et
    -0.65
    us
    -0.64
    _
    -0.63
     N
    -0.62
     h
    -0.60
    POSITIVE LOGITS
     +=
    1.62
    ]+=
    1.43
    +=
    1.30
     ainfi
    1.28
     -=
    1.28
    berdayakan
    1.27
    /=
    1.25
     CreateTagHelper
    1.21
     plufieurs
    1.17
     >=",
    1.16
    Act Density 0.018%

    No Known Activations