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

    Neuronpedia

    INDEX
    Explanations

    typical examples or instances of something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    heed
    -1.14
    inth
    -0.94
    nuts
    -0.92
    acus
    -0.86
    arching
    -0.81
    ternity
    -0.81
    aughter
    -0.80
    bows
    -0.79
    sterdam
    -0.79
    heid
    -0.78
    POSITIVE LOGITS
    istic
    0.99
    ization
    0.98
     deviations
    0.96
    ized
    0.95
     deviation
    0.95
    ised
    0.93
    rities
    0.93
    ãĥīãĥ©ãĤ´ãĥ³
    0.93
    istics
    0.91
    istically
    0.89
    Act Density 1.002%

    No Known Activations