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

    Neuronpedia

    INDEX
    Explanations

    the adjective "ordinary."

    oai_token-act-pair · gpt-4-turbo

    instances of the word 'ordinary'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ordinary."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haw
    -0.67
    hop
    -0.65
    lez
    -0.64
    Stars
    -0.64
    AIDS
    -0.64
    Recomm
    -0.62
    Sov
    -0.61
    Wa
    -0.61
    alez
    -0.60
    OTH
    -0.60
    POSITIVE LOGITS
    ordinary
    1.14
     ordinary
    1.07
     mortals
    1.01
     sized
    0.80
    worldly
    0.78
     mortal
    0.76
     everyday
    0.76
     weekday
    0.75
     folk
    0.73
     human
    0.72
    Act Density 0.006%

    No Known Activations