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

    Neuronpedia

    INDEX
    Explanations

    high-frequency repetitive sequences or patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.15
    ish
    -0.15
    sl
    -0.14
    shot
    -0.13
    ceae
    -0.13
    shit
    -0.13
    iker
    -0.12
    ook
    -0.12
    ore
    -0.12
    vel
    -0.12
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.20
    ythe
    0.17
    forth
    0.16
    ichten
    0.15
    arity
    0.14
    yth
    0.14
    ancel
    0.14
    ÙĬÙĦاد
    0.14
    gel
    0.14
    icont
    0.14
    Act Density 0.053%

    No Known Activations