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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by specific nouns or pronouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redesign
    -0.71
    ertodd
    -0.67
     awa
    -0.67
    ovember
    -0.64
     streng
    -0.63
     tailor
    -0.63
    ÃŁ
    -0.62
     curtain
    -0.60
     rewrite
    -0.59
    irez
    -0.59
    POSITIVE LOGITS
    THING
    0.88
     whatsoever
    0.70
    course
    0.68
    ·
    0.67
    those
    0.67
    these
    0.64
    them
    0.64
     us
    0.64
    things
    0.63
    astical
    0.63
    Act Density 0.060%

    No Known Activations