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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated usage in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ī
    -0.18
    iteli
    -0.18
    eless
    -0.16
    castle
    -0.15
    _ASM
    -0.15
     meiden
    -0.14
    uncia
    -0.14
    getReference
    -0.14
    ogne
    -0.14
    forgettable
    -0.14
    POSITIVE LOGITS
     -
    0.16
    ag
    0.16
    ãĥ©ãĥ¼
    0.15
    zo
    0.15
     Rash
    0.14
    organic
    0.14
     ns
    0.14
    ÙħاÙħ
    0.13
     Mal
    0.13
     /
    0.13
    Act Density 0.449%

    No Known Activations