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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific nouns or phrases related to particular topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joined
    -0.72
    elaide
    -0.65
    tackle
    -0.63
    illion
    -0.63
    ledge
    -0.63
     of
    -0.62
    hari
    -0.62
    etsk
    -0.62
    arten
    -0.62
    ilde
    -0.61
    POSITIVE LOGITS
     latter
    1.25
     aforementioned
    1.14
     utmost
    0.95
     same
    0.92
     smallest
    0.91
     proverbial
    0.91
     dreaded
    0.89
     slightest
    0.89
     greatest
    0.87
    oret
    0.87
    Act Density 0.345%

    No Known Activations