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

    Neuronpedia

    INDEX
    Explanations

    quantities or proportions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proportions or distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.74
    Reviewer
    -0.65
     Psychiat
    -0.65
     pse
    -0.62
     notwithstanding
    -0.59
     wizards
    -0.59
    dayName
    -0.58
     distur
    -0.56
     confir
    -0.55
     disposed
    -0.55
    POSITIVE LOGITS
     his
    0.73
    their
    0.73
     their
    0.72
    tein
    0.71
     himself
    0.66
    folio
    0.65
     its
    0.64
    ossus
    0.64
    ãģĨ
    0.64
    ocobo
    0.64
    Act Density 0.163%

    No Known Activations