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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to Stanford University

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    itte
    -1.23
    uably
    -0.92
     nitrogen
    -0.87
    ichick
    -0.84
    ombo
    -0.82
    ersion
    -0.81
    =/
    -0.81
    ution
    -0.77
     Colossus
    -0.77
    container
    -0.76
    POSITIVE LOGITS
    izo
    1.09
    nee
    1.00
    ews
    0.99
    chal
    0.98
    isl
    0.96
    jong
    0.96
    ning
    0.95
     Stan
    0.93
    vol
    0.90
    boarding
    0.89
    Act Density 0.461%

    No Known Activations