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

    Neuronpedia

    INDEX
    Explanations

    and highlight mentions of flaws or problems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to flaws or deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rollers
    -0.79
     beans
    -0.63
     Carbuncle
    -0.63
    zee
    -0.63
     palms
    -0.62
    oths
    -0.61
    eston
    -0.61
    iversary
    -0.60
    VO
    -0.60
    ista
    -0.59
    POSITIVE LOGITS
    acies
    0.94
     flaws
    0.86
     flaw
    0.82
    lessly
    0.78
    nesses
    0.77
    nah
    0.76
    ulence
    0.76
     plag
    0.75
    iology
    0.70
    iants
    0.69
    Act Density 0.051%

    No Known Activations