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

    Neuronpedia

    INDEX
    Explanations

    tokens related to prefixes or roots commonly used in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lettes
    -0.17
    quin
    -0.16
    iffer
    -0.15
    ervlet
    -0.15
    chez
    -0.15
    GGLE
    -0.14
     Conv
    -0.14
    aversable
    -0.14
    edException
    -0.14
    ợ
    -0.14
    POSITIVE LOGITS
     Falls
    0.16
     seg
    0.14
     tod
    0.14
    ough
    0.14
    (actions
    0.14
    isci
    0.14
    ondere
    0.14
     FALL
    0.14
     Falk
    0.13
    oden
    0.13
    Act Density 0.140%

    No Known Activations