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

    Neuronpedia

    INDEX
    Explanations

    structural elements in code, particularly brackets and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OLL
    -0.15
    ëįķ
    -0.15
    ollar
    -0.15
    hpp
    -0.14
    stell
    -0.14
     ÐĴики
    -0.14
    chner
    -0.14
    urret
    -0.14
    ewriter
    -0.14
     feather
    -0.13
    POSITIVE LOGITS
    gor
    0.16
    pq
    0.15
    rok
    0.15
    rak
    0.14
    ledon
    0.14
    tones
    0.14
    ahir
    0.14
    ãĢħ
    0.13
    ks
    0.13
     rop
    0.13
    Act Density 0.317%

    No Known Activations