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

    Neuronpedia

    INDEX
    Explanations

    expressions related to deficits or absences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ò
    -0.18
    /watch
    -0.16
    umerator
    -0.16
     киÑĪ
    -0.15
     Ñĥж
    -0.15
    hung
    -0.14
    iffies
    -0.14
    _INITIALIZER
    -0.14
    ILLISECONDS
    -0.14
    xbf
    -0.14
    POSITIVE LOGITS
    ened
    0.21
    ening
    0.18
    lust
    0.16
    ling
    0.16
    ert
    0.14
    /errors
    0.14
    ens
    0.14
    kü
    0.14
    ada
    0.14
    mann
    0.14
    Act Density 0.016%

    No Known Activations