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 degrees of manner or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.96
    afety
    -0.79
    VL
    -0.74
    emetery
    -0.73
    ļéĨĴ
    -0.72
    uper
    -0.70
    ession
    -0.70
    quickShipAvailable
    -0.69
    Liter
    -0.68
     Flavoring
    -0.67
    POSITIVE LOGITS
     disposed
    0.82
     titled
    0.81
     discharged
    0.78
    theless
    0.78
     priced
    0.77
     pursued
    0.76
    gged
    0.74
     enough
    0.74
     paced
    0.73
     defended
    0.73
    Act Density 0.081%

    No Known Activations