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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a focus on specifics or necessities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eatured
    -0.75
    leneck
    -0.73
    uese
    -0.72
    nown
    -0.69
    integ
    -0.67
     largeDownload
    -0.66
    orian
    -0.65
    izers
    -0.65
     contag
    -0.63
    eatures
    -0.63
    POSITIVE LOGITS
     annoyance
    0.69
     guesses
    0.69
    Magikarp
    0.67
    Champ
    0.66
     scratch
    0.66
     kidding
    0.65
     scratches
    0.64
     pray
    0.64
     pure
    0.64
    Disclaimer
    0.63
    Act Density 0.078%

    No Known Activations