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

    Neuronpedia

    INDEX
    Explanations

    phrases related to psychological concepts or introspection

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Licensed
    -0.68
     Vide
    -0.64
    Recomm
    -0.63
    DIR
    -0.63
    NRS
    -0.62
     Mehran
    -0.61
    reek
    -0.61
    ModLoader
    -0.61
    Reviewed
    -0.60
     Slay
    -0.60
    POSITIVE LOGITS
    fulness
    1.27
    storms
    1.12
    bender
    1.06
    share
    1.03
    scape
    0.98
    lessly
    0.98
    ets
    0.96
    ful
    0.95
    fuck
    0.92
    iac
    0.92
    Act Density 0.028%

    No Known Activations