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

    Neuronpedia

    INDEX
    Explanations

    words related to physical movement or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'w'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.86
     apprehension
    -0.69
    uate
    -0.69
     depri
    -0.65
    terday
    -0.64
     fracturing
    -0.64
     headache
    -0.64
     unpre
    -0.63
     responsibility
    -0.63
     duplication
    -0.62
    POSITIVE LOGITS
    iggle
    1.21
    ither
    1.21
    atts
    1.15
    alt
    1.14
    atered
    1.12
    affles
    1.11
    ithering
    1.11
    igg
    1.10
    ickets
    1.10
    atson
    1.10
    Act Density 0.018%

    No Known Activations