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

    Neuronpedia

    INDEX
    Explanations

    positive aspects or highlights of items

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.69
    flush
    -0.64
     throats
    -0.64
    igate
    -0.58
     fever
    -0.58
    idelines
    -0.58
     shoulders
    -0.58
    ignt
    -0.56
    æµ
    -0.55
    perature
    -0.55
    POSITIVE LOGITS
     happens
    0.68
     surprises
    0.68
    :{
    0.67
     Flavoring
    0.67
    SPONSORED
    0.66
     thing
    0.64
    uary
    0.64
     happened
    0.64
     Mai
    0.63
     Mara
    0.62
    Act Density 0.084%

    No Known Activations