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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a measurement of distance or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a progression or ongoing status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chio
    -0.69
    vec
    -0.66
    pron
    -0.64
     Lunch
    -0.64
    orem
    -0.63
    olor
    -0.63
     EntityItem
    -0.62
     Replacement
    -0.61
     "%
    -0.61
     Spectrum
    -0.60
    POSITIVE LOGITS
     unsuccessful
    0.76
    ugu
    0.69
     incarnation
    0.66
    fetched
    0.64
    interstitial
    0.64
     unsuccessfully
    0.63
    ago
    0.62
     unrem
    0.62
    -------------
    0.62
    iasm
    0.61
    Act Density 0.035%

    No Known Activations