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

    Neuronpedia

    INDEX
    Explanations

    semicolon usage in code snippets or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.28
    s
    -0.25
    "
    -0.19
    i
    -0.18
    :
    -0.18
    x
    -0.17
    ↵↵
    -0.17
    n
    -0.16
    m
    -0.16
    p
    -0.16
    POSITIVE LOGITS
    enk
    0.15
    illis
    0.15
    ous
    0.14
    ;line
    0.14
     etc
    0.14
    ...↵↵↵↵
    0.13
    ži
    0.13
    ìĹŃ
    0.13
    ldkf
    0.13
    591
    0.13
    Act Density 0.084%

    No Known Activations