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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating an increase or addition

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anship
    -0.80
    ister
    -0.77
    externalActionCode
    -0.76
    Tracker
    -0.75
    otine
    -0.74
    omed
    -0.73
    obar
    -0.71
    ylum
    -0.71
     Yugoslavia
    -0.71
    isine
    -0.70
    POSITIVE LOGITS
     rounds
    0.89
     pieces
    0.88
     inches
    0.87
     layers
    0.85
     weeks
    0.84
     paragraphs
    0.84
     dozen
    0.83
     digits
    0.83
     hundred
    0.82
     installments
    0.82
    Act Density 0.164%

    No Known Activations