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

    Neuronpedia

    INDEX
    Explanations

    words related to medical conditions and health issues

    oai_token-act-pair · gpt-3.5-turbo

    words related to debris or remnants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.67
     salv
    -0.66
     Remem
    -0.66
     reusable
    -0.66
     constitu
    -0.65
     Nun
    -0.65
    OIL
    -0.63
     Corvette
    -0.63
     suspense
    -0.62
     confidence
    -0.61
    POSITIVE LOGITS
    orf
    1.22
    ividual
    1.21
    ynamic
    1.21
    iary
    1.19
    aniel
    1.11
    ynam
    1.05
    roid
    1.05
    iaries
    1.04
    elta
    1.04
    etermin
    1.03
    Act Density 0.055%

    No Known Activations