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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate possession and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.89
     pinulongan
    -0.78
     ―――――
    -0.74
     Silo
    -0.74
     Assim
    -0.73
     Bessie
    -0.72
    Portale
    -0.72
    بوابة
    -0.72
    ῆς
    -0.69
    tamol
    -0.69
    POSITIVE LOGITS
    s
    1.45
    ’
    1.44
    '
    0.89
    )’
    0.87
    €™
    0.83
    ‘
    0.80
    slu
    0.73
    }'
    0.72
    !’
    0.71
    ’.
    0.71
    Act Density 0.411%

    No Known Activations