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

    Neuronpedia

    INDEX
    Explanations

    symbols and special characters followed by specific two-letter combinations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character 'Ķ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sponsor
    -0.66
     Sans
    -0.65
     Franch
    -0.62
    isation
    -0.60
     lur
    -0.60
     Targ
    -0.59
     Fr
    -0.59
     plan
    -0.58
     breach
    -0.58
    stri
    -0.58
    POSITIVE LOGITS
    Ķ
    4.37
    ĵ
    2.13
    IJ
    2.01
    Ĵ
    1.95
    ľ
    1.93
    ij
    1.92
    ĺ
    1.88
    ķ
    1.86
    ļ
    1.84
    İ
    1.80
    Act Density 0.012%

    No Known Activations