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

    Neuronpedia

    INDEX
    Explanations

    religious or mystical symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "ŀ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.69
    abwe
    -0.69
    pton
    -0.68
     Spit
    -0.64
     Spice
    -0.63
    pher
    -0.62
     trainers
    -0.61
    Downloadha
    -0.61
     disenfranch
    -0.60
     manag
    -0.60
    POSITIVE LOGITS
    ŀ
    1.16
    Ĺ
    1.03
    ·
    0.96
    ĵ
    0.95
    ļ
    0.94
    ĺ
    0.92
    IJ
    0.91
    ¬
    0.91
    ³
    0.90
    ł
    0.89
    Act Density 0.006%

    No Known Activations