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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a previous mention or reference in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to prior studies or previous information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lua
    -0.75
    alker
    -0.72
    atron
    -0.72
    asp
    -0.71
    aliation
    -0.70
    rage
    -0.69
    istan
    -0.69
    ifle
    -0.68
    ocracy
    -0.68
    aleigh
    -0.66
    POSITIVE LOGITS
     generations
    1.11
     incarn
    1.06
     iterations
    0.91
     incarnation
    0.84
     administrations
    0.84
     installments
    0.82
    ebin
    0.82
     versions
    0.80
     affili
    0.79
     editions
    0.79
    Act Density 0.027%

    No Known Activations