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

    Neuronpedia

    INDEX
    Explanations

    strings and formatting markers related to code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å£°éŁ³
    -0.20
    ’ta
    -0.17
    edn
    -0.16
     «
    -0.16
    ’t
    -0.16
    ¬ģ
    -0.15
    /OR
    -0.15
    ãĢĮãģĬ
    -0.15
    uxe
    -0.14
    éĹ®é¢ĺ
    -0.14
    POSITIVE LOGITS
    s
    0.18
    <?=$
    0.15
    amp
    0.14
    ÂĢÂ
    0.14
    apesh
    0.14
    {{$
    0.14
    the
    0.13
    eer
    0.13
    TY
    0.13
    rippling
    0.13
    Act Density 0.158%

    No Known Activations