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

    Neuronpedia

    INDEX
    Explanations

    periods in a text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of statements or quotes attributed to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.81
     cradle
    -0.71
     transact
    -0.69
     remnant
    -0.69
     utter
    -0.66
     acknowledgement
    -0.64
    idon
    -0.64
     adulthood
    -0.63
     fleeting
    -0.63
     killers
    -0.62
    POSITIVE LOGITS
    lua
    0.89
     [+
    0.87
    debian
    0.85
    esp
    0.81
    org
    0.80
     Unloaded
    0.79
    np
    0.79
    ajor
    0.75
    jpg
    0.74
     Retrieved
    0.74
    Act Density 0.167%

    No Known Activations