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

    Neuronpedia

    INDEX
    Explanations

    the syllable "ato" within words

    oai_token-act-pair · gpt-4-turbo

    the word "Kratato" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Krakatoa" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HH
    -0.70
     Wolves
    -0.68
    stract
    -0.67
     Vikings
    -0.66
    respect
    -0.65
     Horizons
    -0.65
    drawn
    -0.63
     sclerosis
    -0.61
    der
    -0.61
    mable
    -0.60
    POSITIVE LOGITS
    ichi
    1.22
    cia
    1.06
    ieri
    1.00
    eca
    0.99
    hea
    0.97
    zzi
    0.96
    zeb
    0.95
    oga
    0.93
    zzo
    0.93
    itsu
    0.90
    Act Density 0.010%

    No Known Activations