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

    Neuronpedia

    INDEX
    Explanations

    words related to potential or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence or condition of certain qualities or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erville
    -0.71
    RH
    -0.67
    ussia
    -0.63
     Franch
    -0.63
    ature
    -0.62
     drafts
    -0.61
    orks
    -0.61
    ieves
    -0.61
    atorial
    -0.61
    phrine
    -0.61
    POSITIVE LOGITS
     undeniable
    1.32
     immense
    1.29
     limitless
    1.22
     palpable
    1.21
     negligible
    1.20
     endless
    1.18
     staggering
    1.18
     astounding
    1.17
     obvious
    1.17
     enormous
    1.15
    Act Density 0.200%

    No Known Activations