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

    Neuronpedia

    INDEX
    Explanations

    references to appropriateness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ute
    -0.15
    utes
    -0.15
    wig
    -0.14
    GLOBALS
    -0.14
     Jim
    -0.14
    ved
    -0.14
    ikh
    -0.14
    exterity
    -0.14
    pery
    -0.14
    зи
    -0.13
    POSITIVE LOGITS
    ately
    0.20
    vern
    0.16
    .bz
    0.15
    ÙĪرش
    0.15
    adia
    0.15
    ież
    0.14
    _nsec
    0.14
    odia
    0.14
    licken
    0.14
    STALL
    0.14
    Act Density 0.021%

    No Known Activations