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

    Neuronpedia

    INDEX
    Explanations

    references to the absence or non-existence of values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iba
    -0.18
    warn
    -0.16
     correct
    -0.15
    eper
    -0.15
    ();)
    -0.14
    иÑĢов
    -0.14
     Kin
    -0.13
     Ekon
    -0.13
    çĶ»
    -0.13
    CAF
    -0.13
    POSITIVE LOGITS
    axed
    0.16
    agrant
    0.15
    oux
    0.15
    amma
    0.15
    phe
    0.14
     ucwords
    0.14
    leness
    0.14
    æ¶
    0.14
    ultan
    0.14
    ุà¸ļ
    0.14
    Act Density 0.002%

    No Known Activations