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

    Neuronpedia

    INDEX
    Explanations

    quotations or statements followed by punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly the period and exclamation mark

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     veter
    -0.66
    gypt
    -0.64
    gettable
    -0.64
    undai
    -0.63
    iliated
    -0.63
     daring
    -0.62
    otin
    -0.62
    ²¾
    -0.61
    ģ«
    -0.61
    userc
    -0.61
    POSITIVE LOGITS
     âĢķ
    1.24
     -
    0.99
    <|endoftext|>
    0.99
     –
    0.97
     ~
    0.97
    ↵
    0.97
     —
    0.96
     Says
    0.95
     exclaimed
    0.89
    ↵↵
    0.89
    Act Density 0.100%

    No Known Activations