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

    Neuronpedia

    INDEX
    Explanations

    specific patterns or sequences of characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulty
    -0.18
    elow
    -0.16
    _simps
    -0.16
    ymoon
    -0.15
    ây
    -0.15
     èĤ
    -0.15
    aden
    -0.15
     duplex
    -0.14
    psz
    -0.14
    aby
    -0.14
    POSITIVE LOGITS
     Ne
    0.17
    éı¡
    0.17
     fists
    0.16
     Foreign
    0.16
    erver
    0.16
    erli
    0.16
     Champ
    0.15
     Rap
    0.15
     foreign
    0.15
    foreign
    0.15
    Act Density 0.005%

    No Known Activations