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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating descriptions or classifications of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afort
    -0.15
    usta
    -0.15
     dela
    -0.15
    ä»ķ
    -0.14
    اسÙħ
    -0.14
    eyJ
    -0.14
    ãĥ¼ãĥ
    -0.14
    Nej
    -0.13
    stdClass
    -0.13
    isse
    -0.13
    POSITIVE LOGITS
     sebagai
    0.21
     as
    0.19
    arch
    0.17
    acific
    0.15
     gener
    0.14
     differently
    0.14
     jako
    0.14
    bers
    0.14
    oop
    0.13
     ind
    0.13
    Act Density 0.074%

    No Known Activations