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

    Neuronpedia

    INDEX
    Explanations

    questions in the text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly question marks and exclamation points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -1.04
    tackle
    -0.81
    —"
    -0.74
    -"
    -0.73
     incentiv
    -0.61
    shaw
    -0.60
    amazon
    -0.59
    —
    -0.57
    –
    -0.57
    mails
    -0.56
    POSITIVE LOGITS
     !
    2.76
     ?
    2.76
     !!
    1.88
     ??
    1.72
     ;
    1.57
     :
    1.46
     .
    1.44
     ?)
    1.40
     ^
    1.40
     ???
    1.40
    Act Density 0.014%

    No Known Activations