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

    Neuronpedia

    INDEX
    Explanations

    forms of the word "won" and its variations, indicating victory or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÂĿ
    -0.17
    еÑİ
    -0.16
    lyn
    -0.16
    enny
    -0.15
    tre
    -0.15
    ей
    -0.15
    zac
    -0.14
    echa
    -0.14
    erç
    -0.14
    ett
    -0.14
    POSITIVE LOGITS
    't
    0.30
    ’t
    0.28
    kish
    0.21
    ldr
    0.18
    ky
    0.18
    ner
    0.17
    ildo
    0.16
    DER
    0.16
    rg
    0.16
    nt
    0.16
    Act Density 0.080%

    No Known Activations