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

    Neuronpedia

    INDEX
    Explanations

    proper nouns in the format "X.X." where X represents letters or abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "J" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holders
    -0.88
    holder
    -0.75
    dayName
    -0.70
    ãĤ¤ãĥĪ
    -0.65
    ciation
    -0.63
     Soviets
    -0.62
    mble
    -0.62
    TPPStreamerBot
    -0.61
     priv
    -0.61
     captcha
    -0.61
    POSITIVE LOGITS
    upiter
    1.27
    ournals
    1.25
    ealous
    1.24
    unction
    1.12
    acket
    1.11
    ihad
    1.05
    igsaw
    1.04
    OY
    1.03
    ansen
    1.03
    umper
    1.01
    Act Density 0.041%

    No Known Activations