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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ény
    -0.15
    enda
    -0.15
    ady
    -0.15
    :
    -0.14
    ennes
    -0.14
    mando
    -0.14
    ing
    -0.13
    endl
    -0.13
    رد
    -0.13
    ÑĩаÑģÑĤ
    -0.13
    POSITIVE LOGITS
    shm
    0.16
    mil
    0.16
     alg
    0.15
    ÃĹ↵↵
    0.15
    ONG
    0.15
     Loads
    0.14
    ORG
    0.14
    егоÑĢ
    0.14
    akra
    0.14
    ONS
    0.13
    Act Density 0.038%

    No Known Activations