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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     otherwise
    -0.17
     Otherwise
    -0.15
    aney
    -0.14
    otherwise
    -0.14
     OTHERWISE
    -0.13
     skeleton
    -0.13
    pecially
    -0.13
    quiring
    -0.13
    uta
    -0.13
    orough
    -0.12
    POSITIVE LOGITS
    try
    0.19
     try
    0.17
     Try
    0.16
    kker
    0.16
     UPDATED
    0.16
    ###↵↵
    0.16
     There
    0.15
    You
    0.15
    There
    0.15
     You
    0.15
    Act Density 0.028%

    No Known Activations