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

    Neuronpedia

    INDEX
    Explanations

    punctuation and syntax elements in code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qed
    -0.16
    implify
    -0.15
    âce
    -0.14
    utenberg
    -0.14
    MLS
    -0.14
    بش
    -0.14
    ilim
    -0.14
    alto
    -0.14
     OTHERWISE
    -0.13
    &action
    -0.13
    POSITIVE LOGITS
    .openConnection
    0.15
     Trev
    0.14
     Ñĥп
    0.14
    reet
    0.14
    alis
    0.14
    ÂĿ
    0.13
     sposób
    0.13
    aname
    0.13
     gist
    0.13
    ól
    0.13
    Act Density 0.147%

    No Known Activations