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

    Neuronpedia

    INDEX
    Explanations

    verbs related to making changes or adjustments

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases indicating changes or adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atu
    -0.73
    anie
    -0.71
    anasia
    -0.68
    oliberal
    -0.67
    oplan
    -0.66
    isters
    -0.64
    ONY
    -0.63
    rouse
    -0.63
    cong
    -0.63
    bleacher
    -0.63
    POSITIVE LOGITS
     everything
    0.83
     it
    0.80
     them
    0.77
     things
    0.75
     the
    0.73
     gears
    0.72
     expectations
    0.72
     usability
    0.71
     its
    0.70
     terminology
    0.68
    Act Density 0.261%

    No Known Activations