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

    Neuronpedia

    INDEX
    Explanations

    proper nouns such as names of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of organizations, locations, and significant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exception
    -0.66
     hypothesis
    -0.65
     aspect
    -0.62
    eanor
    -0.61
     deduction
    -0.61
     characteristic
    -0.60
    problem
    -0.60
     variant
    -0.58
    ibliography
    -0.58
     example
    -0.57
    POSITIVE LOGITS
     Studios
    0.90
     Magazine
    0.77
     Productions
    0.75
     Airlines
    0.73
    's
    0.73
     fame
    0.73
     Airways
    0.73
     Stadium
    0.72
     Boulevard
    0.71
     magazine
    0.71
    Act Density 0.629%

    No Known Activations