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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending in 'ly' that typically describe behaviors or actions with an emphasis on the intensity of the action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.91
    afety
    -0.83
    ļéĨĴ
    -0.76
    ilater
    -0.75
    VL
    -0.73
    OTOS
    -0.73
    ession
    -0.72
    itures
    -0.69
    emetery
    -0.68
    raltar
    -0.68
    POSITIVE LOGITS
     priced
    0.84
     titled
    0.82
    bus
    0.74
    present
    0.73
     discharged
    0.73
     sized
    0.72
     disposed
    0.72
    named
    0.71
     labelled
    0.71
    forward
    0.71
    Act Density 0.088%

    No Known Activations