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

    Neuronpedia

    INDEX
    Explanations

    names of people, especially historical figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    comed
    -1.06
    umpy
    -1.05
    intern
    -1.00
    comings
    -0.99
    icky
    -0.97
    REL
    -0.95
    risome
    -0.95
    efficients
    -0.93
    EEP
    -0.93
    aryl
    -0.92
    POSITIVE LOGITS
     III
    1.06
    sson
    1.05
     Roberts
    1.04
     Hubbard
    1.02
     Hes
    1.00
     Rodrig
    1.00
     Militia
    0.99
    ovich
    0.97
     Tenth
    0.94
     Gib
    0.94
    Act Density 1.655%

    No Known Activations