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

    Neuronpedia

    INDEX
    Explanations

    occurrences of non-Latin characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é
    -0.16
    es
    -0.15
    arella
    -0.15
     Bull
    -0.14
    xd
    -0.14
     weak
    -0.14
    Ħĸ
    -0.14
    ow
    -0.14
    æ¼
    -0.14
    orsk
    -0.14
    POSITIVE LOGITS
    ĺ
    0.35
    Ĵ
    0.28
    Ļ
    0.27
    ļ
    0.26
    Ľ
    0.25
    ķ
    0.21
    ambre
    0.18
    IJ
    0.17
    ¡
    0.17
    ł
    0.16
    Act Density 0.004%

    No Known Activations