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

    Neuronpedia

    INDEX
    Explanations

    statistical patterns and data

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.83
    dylib
    -0.66
    \.
    -0.64
    wow
    -0.62
    ibe
    -0.61
    cin
    -0.60
    ERG
    -0.60
    JD
    -0.59
    paren
    -0.58
    manac
    -0.57
    POSITIVE LOGITS
     progressively
    0.94
     passively
    0.91
     freely
    0.88
     arbitrarily
    0.85
     randomly
    0.84
     perpetually
    0.82
     unilaterally
    0.81
     seamlessly
    0.81
     constantly
    0.80
     pitted
    0.80
    Act Density 0.641%

    No Known Activations