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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wonderful."

    oai_token-act-pair · gpt-3.5-turbo

    the word "wonderful" and its expressions of positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olate
    -0.80
    gemony
    -0.78
    ©¶æ
    -0.77
    atum
    -0.76
    avis
    -0.75
    pper
    -0.71
    resy
    -0.71
    PD
    -0.70
    opers
    -0.70
    arers
    -0.70
    POSITIVE LOGITS
    terday
    0.74
     sounding
    0.73
    NESS
    0.72
     joy
    0.72
     wonderful
    0.70
     little
    0.70
     gracious
    0.69
     Samar
    0.69
     pleasure
    0.69
     congratulations
    0.68
    Act Density 0.014%

    No Known Activations