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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate dialogue or emotional expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.71
     Maid
    -0.66
     Sof
    -0.63
     Amir
    -0.62
    uron
    -0.60
     Pesh
    -0.59
     Yuk
    -0.58
     Mug
    -0.57
     Leban
    -0.57
    utenant
    -0.56
    POSITIVE LOGITS
    SPONSORED
    0.86
    />
    0.73
    <|endoftext|>
    0.69
    Iter
    0.69
     âĸ
    0.68
    ↵
    0.65
    Statement
    0.65
     >>>
    0.65
     ###
    0.65
    index
    0.64
    Act Density 0.212%

    No Known Activations