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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is quoted as saying something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inary
    -0.80
    spir
    -0.71
    rats
    -0.71
    eneg
    -0.69
    acts
    -0.69
    empt
    -0.68
    aired
    -0.67
    rel
    -0.65
    icates
    -0.65
    illus
    -0.64
    POSITIVE LOGITS
     Jonathan
    0.81
     David
    0.79
     Dawn
    0.79
    ï¸ı
    0.79
     Pamela
    0.78
     Laura
    0.78
     Joyce
    0.78
     Quartz
    0.77
     Polly
    0.76
     Joel
    0.76
    Act Density 0.034%

    No Known Activations