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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending in 'ly'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that convey a sense of action or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.71
     Kelvin
    -0.67
    itu
    -0.67
     GOODMAN
    -0.65
    icans
    -0.64
    elo
    -0.63
     Resistance
    -0.63
    ickets
    -0.63
     Horizons
    -0.62
    afety
    -0.62
    POSITIVE LOGITS
     performed
    0.78
     transitioned
    0.77
     screened
    0.76
     discharged
    0.75
    zed
    0.73
    ilus
    0.73
     conclud
    0.71
    wash
    0.71
     entertained
    0.70
     produced
    0.69
    Act Density 0.051%

    No Known Activations