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

    Neuronpedia

    INDEX
    Explanations

    occurrences of code block delimiters, specifically backticks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sei
    -0.17
    lfw
    -0.15
    batim
    -0.14
    ноÑĩ
    -0.14
    aises
    -0.14
    furt
    -0.14
     Bark
    -0.14
    ó
    -0.14
     bol
    -0.14
     cent
    -0.14
    POSITIVE LOGITS
    elines
    0.16
    son
    0.16
    abel
    0.15
    zo
    0.14
    er
    0.14
    ove
    0.14
    è
    0.13
    IfNeeded
    0.13
    lesi
    0.13
    Logic
    0.13
    Act Density 0.006%

    No Known Activations