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

    Neuronpedia

    INDEX
    Explanations

    comma characters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     misunder
    -0.66
     disadvant
    -0.63
     destro
    -0.63
    ally
    -0.63
     spont
    -0.63
     blasphemy
    -0.63
     vulner
    -0.61
     peg
    -0.61
     toes
    -0.61
    itiz
    -0.60
    POSITIVE LOGITS
    actionDate
    0.82
    hov
    0.69
    à¼
    0.68
    taboola
    0.68
    mosp
    0.66
     Psy
    0.65
     ][
    0.65
    ojure
    0.65
    tor
    0.64
    080
    0.63
    Act Density 0.056%

    No Known Activations