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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thumbnails
    -0.71
    renheit
    -0.63
    ardless
    -0.63
    adelphia
    -0.63
    CEPT
    -0.62
    imming
    -0.61
    aturday
    -0.60
    ĵĺ
    -0.60
     minus
    -0.60
     âĸº
    -0.60
    POSITIVE LOGITS
     said
    1.51
     says
    1.44
     wrote
    1.42
     told
    1.34
     explained
    1.32
     explains
    1.31
     writes
    1.31
     remarked
    1.26
     tells
    1.25
     replied
    1.21
    Act Density 0.190%

    No Known Activations