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

    Neuronpedia

    INDEX
    Explanations

    phonetic patterns and unusual segmentations of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayi
    -0.15
    orra
    -0.15
     conf
    -0.14
    uchs
    -0.14
    \Carbon
    -0.14
    ĶåĽŀ
    -0.13
    æĶ¯
    -0.13
    нÑĸÑĩ
    -0.13
     tertiary
    -0.13
    ourg
    -0.13
    POSITIVE LOGITS
    kers
    0.16
    etch
    0.16
    ardin
    0.16
    shint
    0.15
    miss
    0.15
    ophon
    0.14
     cá
    0.14
    ainless
    0.14
     SV
    0.14
    illin
    0.14
    Act Density 0.266%

    No Known Activations