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

    Neuronpedia

    INDEX
    Explanations

    sequences of formatting characters or symbols in technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erna
    -0.19
    اÙĨÙĩ
    -0.16
    ationship
    -0.16
    erm
    -0.16
    ses
    -0.16
    irie
    -0.15
    ãĥ«ãĥķ
    -0.15
    entials
    -0.15
    мовÑĸÑĢ
    -0.14
    ằm
    -0.14
    POSITIVE LOGITS
    kwargs
    0.24
    *(
    0.21
    */
    0.21
    *>
    0.20
    *)
    0.19
    ³³³³³
    0.18
    ician
    0.18
    ³³³³³³³
    0.18
    ³³³³³³³³
    0.18
    /***
    0.17
    Act Density 0.041%

    No Known Activations