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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax elements such as parentheses, braces, and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ôn
    -0.18
    vida
    -0.18
    641
    -0.17
    folio
    -0.17
    667
    -0.17
    -0.15
     nes
    -0.15
    877
    -0.14
    pbs
    -0.14
    917
    -0.14
    POSITIVE LOGITS
    0.28
    0.18
    0.16
    60
    0.16
    Į
    0.15
     Emma
    0.15
    0.15
    Emma
    0.15
    0.15
    0.14
    Act Density 0.091%

    No Known Activations