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

    Neuronpedia

    INDEX
    Explanations

    substrings that start with 'sub'

    oai_token-act-pair · gpt-3.5-turbo

    references to substandard conditions or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESCO
    -0.88
    OHN
    -0.86
     GOODMAN
    -0.83
     Qiao
    -0.83
     )]
    -0.77
    HCR
    -0.75
     Lauderdale
    -0.75
    assetsadobe
    -0.74
    IELD
    -0.73
     Cors
    -0.72
    POSITIVE LOGITS
    missive
    1.20
    mitter
    1.07
    plet
    1.04
    species
    1.03
    sequently
    1.01
    ordinate
    1.00
    atomic
    0.99
    sequent
    0.99
    oter
    0.96
    missible
    0.95
    Act Density 0.009%

    No Known Activations