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

    Neuronpedia

    INDEX
    Explanations

    the word "ite" with varying activation values

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ington
    -0.91
    INGTON
    -0.87
    ood
    -0.85
    nut
    -0.82
    nuts
    -0.81
    wards
    -0.80
    noon
    -0.77
    SIGN
    -0.75
    loo
    -0.74
     NCT
    -0.73
    POSITIVE LOGITS
    chnology
    1.26
    lli
    1.23
    geist
    0.95
    llo
    0.83
    lla
    0.83
    eer
    0.77
    gregation
    0.75
    chn
    0.74
     Scotia
    0.73
    xt
    0.72
    Act Density 0.045%

    No Known Activations