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

    Neuronpedia

    INDEX
    Explanations

    instances of variable declarations and types in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    …
    -0.23
     ‘
    -0.21
    N
    -0.20
    D
    -0.20
     wiedzy
    -0.20
     rekening
    -0.19
    K
    -0.18
     “
    -0.18
    M
    -0.17
    L
    -0.17
    POSITIVE LOGITS
    UrlResolution
    1.09
     ब्रेकडाउन
    0.98
    majánló
    0.98
    RenderAtEndOf
    0.93
    rungsseite
    0.93
     autorytatywna
    0.91
    uxxxx
    0.90
    sizeCache
    0.88
    ﹧
    0.86
     ProtoMessage
    0.84
    Act Density 0.615%

    No Known Activations