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

    Neuronpedia

    INDEX
    Explanations

    social media handles or usernames made up of alphanumeric characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    non-standard characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tid
    -0.76
     laz
    -0.70
     Lazarus
    -0.70
    itar
    -0.68
     Bernstein
    -0.65
    unks
    -0.65
     Winston
    -0.63
    folk
    -0.63
     Sle
    -0.63
     interf
    -0.62
    POSITIVE LOGITS
    Į
    2.37
    İ
    1.99
    ĩ
    1.96
    Ĵ
    1.96
    ı
    1.92
    Ķ
    1.91
    į
    1.91
    ļ
    1.89
    IJ
    1.88
    ĵ
    1.87
    Act Density 0.020%

    No Known Activations