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

    Neuronpedia

    INDEX
    Explanations

    adverbs and adjectives ending in 'ally'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs ending in "-ly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rapp
    -0.69
    oresc
    -0.69
     paycheck
    -0.68
     fellow
    -0.65
    soDeliveryDate
    -0.64
     costumes
    -0.63
     commissioners
    -0.62
     natives
    -0.62
     dancers
    -0.62
     CY
    -0.61
    POSITIVE LOGITS
     differentiated
    0.80
    important
    0.74
    Ü
    0.74
    oxic
    0.72
    Important
    0.71
    ocal
    0.71
     researched
    0.69
    inction
    0.69
    ailed
    0.69
    nit
    0.69
    Act Density 0.036%

    No Known Activations