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

    Neuronpedia

    INDEX
    Explanations

    content related to newsletters from the New York Times

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bender
    -0.64
    aimon
    -0.61
     homebrew
    -0.60
     UD
    -0.59
    idious
    -0.56
    ton
    -0.54
     monog
    -0.54
    atar
    -0.52
     manif
    -0.52
     Comet
    -0.52
    POSITIVE LOGITS
    push
    0.81
    interstitial
    0.74
    ramid
    0.68
    ource
    0.62
    ordial
    0.60
    usat
    0.60
    adden
    0.59
    士
    0.58
    illary
    0.57
    STEM
    0.57
    Act Density 0.045%

    No Known Activations