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

    Neuronpedia

    INDEX
    Explanations

    special characters or unique symbols in various languages or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istol
    -0.16
    STALL
    -0.16
    sterdam
    -0.15
    zug
    -0.15
    zig
    -0.15
    avan
    -0.14
    elsea
    -0.14
    ILLISECONDS
    -0.14
    ERSION
    -0.14
    fold
    -0.14
    POSITIVE LOGITS
    ı
    0.15
    vers
    0.15
    unce
    0.14
    _UTF
    0.14
    affen
    0.14
    iko
    0.14
     Bowman
    0.14
    ending
    0.14
     Dixon
    0.14
    iqu
    0.13
    Act Density 0.009%

    No Known Activations