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

    Neuronpedia

    INDEX
    Explanations

    items or products within a list

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    otle
    -0.84
    gerald
    -0.78
    enegger
    -0.76
    ured
    -0.73
    eful
    -0.72
    uration
    -0.71
    aukee
    -0.70
    urated
    -0.69
    isconsin
    -0.69
    uity
    -0.68
    POSITIVE LOGITS
    nd
    1.88
     thirds
    1.33
    ND
    1.01
     halves
    1.00
     externalToEVAOnly
    0.81
    147
    0.79
    160
    0.77
    133
    0.77
    aries
    0.76
    entary
    0.72
    Act Density 4.254%

    No Known Activations