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

    Neuronpedia

    INDEX
    Explanations

    instances of commas in the text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©
    -0.62
    coni
    -0.61
    avorite
    -0.59
     redund
    -0.58
     explan
    -0.57
     thous
    -0.55
     blat
    -0.55
    ithub
    -0.54
     [*
    -0.53
    Tokens
    -0.53
    POSITIVE LOGITS
     huh
    0.79
     etc
    0.73
     please
    0.68
     partName
    0.66
    usalem
    0.66
     albeit
    0.63
    please
    0.63
     LLC
    0.61
    govtrack
    0.60
    ruct
    0.58
    Act Density 0.167%

    No Known Activations