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

    Neuronpedia

    INDEX
    Explanations

    adverbs related to frequency or certainty

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    regate
    -0.79
    ortmund
    -0.74
    would
    -0.74
    doms
    -0.71
    might
    -0.70
    ipeg
    -0.70
    inav
    -0.69
     scares
    -0.65
    izes
    -0.65
     Increases
    -0.64
    POSITIVE LOGITS
     supposed
    1.07
     considered
    1.02
     going
    1.01
     able
    1.01
     gonna
    0.93
     concerned
    0.91
     capable
    0.90
     undergoing
    0.90
     slated
    0.89
     regarded
    0.89
    Act Density 0.476%

    No Known Activations