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

    Neuronpedia

    INDEX
    Explanations

    dates written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     answ
    -0.87
     administrator
    -0.77
    ween
    -0.71
    matically
    -0.71
    omorphic
    -0.68
     footing
    -0.68
    Ĥª
    -0.68
    rament
    -0.67
    hang
    -0.67
    itory
    -0.66
    POSITIVE LOGITS
    )].
    0.87
     Frames
    0.80
     )]
    0.79
    ])
    0.79
    ãĥİ
    0.77
     Syndicate
    0.73
    )))
    0.72
    esm
    0.71
     âĵĺ
    0.70
     Conversion
    0.70
    Act Density 0.159%

    No Known Activations