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

    Neuronpedia

    INDEX
    Explanations

    adverbs that end in "-ly"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "naturally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blades
    -0.73
    pled
    -0.72
    seless
    -0.70
    raints
    -0.69
     Straw
    -0.69
    INGS
    -0.69
     Execution
    -0.68
     Millennium
    -0.68
    rik
    -0.67
     Horizons
    -0.66
    POSITIVE LOGITS
     occurring
    0.92
     regenerate
    0.82
     arises
    0.77
     regener
    0.77
     attracted
    0.76
     dissip
    0.74
     inclined
    0.74
     instinct
    0.74
     generates
    0.73
     evolve
    0.73
    Act Density 0.015%

    No Known Activations