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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and other punctuation associated with dialogue or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Quotation marks followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    quoted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ‘
    -1.08
     «
    -0.97
    ,
    -0.73
    )
    -0.65
    </h3>
    -0.65
    </h5>
    -0.64
     to
    -0.63
     and
    -0.61
     â
    -0.59
     da
    -0.58
    POSITIVE LOGITS
     pleaſure
    1.46
     purpoſe
    1.38
     ſtate
    1.36
     myſelf
    1.36
     greateſt
    1.34
     reaſon
    1.32
    .."
    1.26
    >"
    1.25
     leaſt
    1.24
     raiſ
    1.24
    Act Density 0.252%

    No Known Activations