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

    Neuronpedia

    INDEX
    Explanations

    references to errors, corrections, and inaccuracies in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -badge
    -0.16
    Argb
    -0.15
     onFailure
    -0.15
     incompetent
    -0.14
     incompet
    -0.14
    ä¸į好
    -0.14
     incompetence
    -0.14
     incap
    -0.13
    mong
    -0.13
    fallback
    -0.13
    POSITIVE LOGITS
     ty
    0.44
     typ
    0.36
     Typ
    0.33
     errors
    0.31
     Ty
    0.31
     spelling
    0.31
     miss
    0.29
    _ty
    0.29
     typo
    0.29
     TYPO
    0.28
    Act Density 0.123%

    No Known Activations