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

    Neuronpedia

    INDEX
    Explanations

    mentions of product names and technical specifications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    */(
    -1.14
    esses
    -0.95
    agan
    -0.87
    otta
    -0.87
    emouth
    -0.84
    oids
    -0.83
    ebin
    -0.81
    ette
    -0.80
    ulhu
    -0.80
     disse
    -0.79
    POSITIVE LOGITS
    Wide
    0.98
    STD
    0.96
    ©
    0.94
    Fram
    0.91
    VID
    0.90
    Fighting
    0.81
    PIN
    0.79
    Safety
    0.77
    Dex
    0.77
    DOC
    0.76
    Act Density 0.483%

    No Known Activations