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

    Neuronpedia

    INDEX
    Explanations

    references to utility classes or functionalities in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angkan
    -0.16
    holm
    -0.15
    ategy
    -0.15
    inia
    -0.15
    گاÙĩ
    -0.15
    ses
    -0.14
    nesia
    -0.14
    δά
    -0.14
    edi
    -0.14
    itet
    -0.14
    POSITIVE LOGITS
    ennon
    0.16
    PRI
    0.15
    iteral
    0.14
    cko
    0.14
    nowrap
    0.14
    ÃĹ↵↵
    0.14
     Prism
    0.14
    تÙĪاÙĨ
    0.14
    uger
    0.13
    posable
    0.13
    Act Density 0.006%

    No Known Activations