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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the use of something by someone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.73
    odiac
    -0.70
    ancock
    -0.68
    iatus
    -0.67
    ufact
    -0.66
    usalem
    -0.65
    rolog
    -0.65
    ukemia
    -0.64
    inois
    -0.63
    cember
    -0.63
    POSITIVE LOGITS
     same
    1.00
     hashtag
    0.99
     restroom
    0.93
     analogy
    0.90
     phrase
    0.89
     pseudonym
    0.89
     opportunity
    0.88
     excuse
    0.88
     tactic
    0.85
     technique
    0.84
    Act Density 0.109%

    No Known Activations