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

    Neuronpedia

    INDEX
    Explanations

    explicit numerical values or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    543
    -0.17
    294
    -0.17
    265
    -0.17
    -0.16
    282
    -0.16
    245
    -0.16
    259
    -0.15
    333
    -0.15
    890
    -0.15
    z
    -0.15
    POSITIVE LOGITS
    uts
    0.17
    -UA
    0.14
    æľ¯
    0.14
    ó
    0.14
    uth
    0.14
    segue
    0.14
    ipp
    0.14
    rys
    0.13
    .jquery
    0.13
    ublic
    0.13
    Act Density 1.329%

    No Known Activations