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

    Neuronpedia

    INDEX
    Explanations

    terms associated with classification or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    én
    -0.15
    adium
    -0.15
    witter
    -0.14
    ADX
    -0.14
    PTS
    -0.14
    atos
    -0.14
     nos
    -0.14
     Morris
    -0.14
    ibu
    -0.14
    esson
    -0.14
    POSITIVE LOGITS
    éĸĢ
    0.17
    iki
    0.17
     acid
    0.16
    éħ¸
    0.15
    roman
    0.15
     Acid
    0.15
    λι
    0.15
     pun
    0.15
     acids
    0.14
    iyan
    0.14
    Act Density 0.027%

    No Known Activations