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

    Neuronpedia

    INDEX
    Explanations

    television show titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    seless
    -0.71
     Beir
    -0.71
    unia
    -0.70
    inator
    -0.67
     plur
    -0.65
     turb
    -0.64
    liness
    -0.64
     oun
    -0.64
    agos
    -0.62
     force
    -0.62
    POSITIVE LOGITS
     (*
    0.86
    (*
    0.80
    #$
    0.75
    Madison
    0.75
    Thompson
    0.72
    Premium
    0.72
    âĢł
    0.72
    âĨij
    0.72
     Shards
    0.71
    Deal
    0.70
    Act Density 0.013%

    No Known Activations