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

    Neuronpedia

    INDEX
    Explanations

    references to legal proceedings and governmental actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Debor
    -1.08
    osuke
    -1.05
     Mahmoud
    -0.95
     sidx
    -0.89
    ipers
    -0.88
     gauge
    -0.85
    eton
    -0.85
     Seym
    -0.84
     Kenobi
    -0.83
    ittal
    -0.82
    POSITIVE LOGITS
    same
    1.10
    internet
    1.08
    atre
    1.08
    ngth
    1.05
    great
    1.02
    self
    1.01
    ological
    0.95
    ounds
    0.95
    gm
    0.94
    best
    0.94
    Act Density 0.230%

    No Known Activations