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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or concepts starting with the letter 'G'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.93
     vou
    -0.66
     htt
    -0.66
    stic
    -0.65
     sight
    -0.63
    =-=-
    -0.63
     Doct
    -0.63
    nsics
    -0.61
    kefeller
    -0.61
     Antiqu
    -0.60
    POSITIVE LOGITS
    asp
    1.16
    ossip
    0.99
    irlfriend
    0.94
    GT
    0.93
    affe
    0.93
    CHQ
    0.93
    rowth
    0.93
    ONE
    0.93
    eeks
    0.92
    ather
    0.92
    Act Density 0.031%

    No Known Activations