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

    Neuronpedia

    INDEX
    Explanations

    punctuations and operators used in code expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubit
    -0.15
    inç
    -0.14
    र
    -0.14
    ï¼Īå¹³æĪIJ
    -0.14
    ober
    -0.14
    ghan
    -0.14
    odi
    -0.14
    er
    -0.14
    دÙĩ
    -0.14
    rottle
    -0.14
    POSITIVE LOGITS
    scribe
    0.19
    uate
    0.16
    'gc
    0.14
    cribe
    0.14
    eros
    0.14
    _finalize
    0.14
     Winter
    0.14
    ãĤ¯ãĥĪ
    0.14
    zo
    0.13
    ìĽĥ
    0.13
    Act Density 0.125%

    No Known Activations