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

    Neuronpedia

    INDEX
    Explanations

    words related to disorder, confusion, and instability

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of disorder and confusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itely
    -0.70
     Kits
    -0.68
    eared
    -0.63
    ACTED
    -0.62
     Cert
    -0.60
     compliment
    -0.60
    haps
    -0.60
    nesium
    -0.60
    arers
    -0.59
    ortium
    -0.59
    POSITIVE LOGITS
     wrought
    1.05
     ensued
    1.04
     engulf
    1.04
     caused
    1.00
     surrounding
    0.97
     plag
    0.95
     arising
    0.92
     ens
    0.90
    rained
    0.88
     disorder
    0.85
    Act Density 0.157%

    No Known Activations