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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific Unicode characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adaptations
    -0.15
     adaptation
    -0.15
    rowable
    -0.14
    ofire
    -0.14
    oze
    -0.13
    lero
    -0.13
    (Locale
    -0.13
    ibold
    -0.13
    è§
    -0.13
     adap
    -0.13
    POSITIVE LOGITS
     allev
    0.29
     dramatically
    0.28
     significantly
    0.27
     drastically
    0.27
     greatly
    0.26
     alleviate
    0.24
     saved
    0.23
    Elim
    0.22
     relieved
    0.22
     substantially
    0.22
    Act Density 0.022%

    No Known Activations