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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to people or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.60
     ..."
    -0.50
     solely
    -0.49
     reef
    -0.48
     Skydragon
    -0.48
    nect
    -0.47
     whichever
    -0.47
     basket
    -0.47
     ÏĦ
    -0.47
     decimal
    -0.46
    POSITIVE LOGITS
    resa
    1.05
    odore
    1.04
    romeda
    0.89
    notations
    0.87
    mosp
    0.79
    withstanding
    0.78
    etheless
    0.78
    xiety
    0.78
    swers
    0.73
    nsic
    0.72
    Act Density 0.886%

    No Known Activations