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

    Neuronpedia

    INDEX
    Explanations

    adjectives or nouns ending in '-ing'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sitting" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sensed
    -0.73
    catentry
    -0.71
    diagn
    -0.70
    otropic
    -0.63
     accompanying
    -0.61
     awa
    -0.61
     overc
    -0.60
    advertisement
    -0.60
    Zen
    -0.60
     dise
    -0.59
    POSITIVE LOGITS
    unes
    0.86
    ters
    0.84
    chens
    0.83
    iton
    0.82
    gerald
    0.79
    oggle
    0.73
    chen
    0.73
    arity
    0.72
    sburgh
    0.72
    ivities
    0.71
    Act Density 0.010%

    No Known Activations