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

    Neuronpedia

    INDEX
    Explanations

    phrases or names of specific entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "known" and its usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plet
    -0.88
    rentice
    -0.80
    ajo
    -0.79
    otion
    -0.78
    ertation
    -0.78
    lot
    -0.76
    otom
    -0.74
    olicy
    -0.74
    odder
    -0.74
    erva
    -0.73
    POSITIVE LOGITS
    ledged
    0.87
    л
    0.86
    itarian
    0.79
    cut
    0.72
    lege
    0.71
     quantity
    0.71
    ties
    0.70
     newsp
    0.70
    Ô
    0.69
     Known
    0.69
    Act Density 0.037%

    No Known Activations