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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and structures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mastur
    -0.16
    们
    -0.15
    beeld
    -0.14
    etine
    -0.14
    antity
    -0.14
    eyin
    -0.14
    .LENGTH
    -0.14
    çIJĨ
    -0.14
    undy
    -0.13
     UNUSED
    -0.13
    POSITIVE LOGITS
    .rawValue
    0.20
    |m
    0.16
     conj
    0.15
    lined
    0.14
    _ONLY
    0.14
    atta
    0.14
     |
    0.14
    /tiny
    0.14
     or
    0.14
    tons
    0.14
    Act Density 0.263%

    No Known Activations