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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with data points or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     All
    -0.15
     Rus
    -0.15
    etting
    -0.14
    ulus
    -0.14
     flat
    -0.14
    моÑĢ
    -0.14
    mdir
    -0.14
     crim
    -0.14
     Hamm
    -0.13
     seek
    -0.13
    POSITIVE LOGITS
    ocal
    0.16
    endcode
    0.15
    kul
    0.15
    ocale
    0.14
    assen
    0.14
    cit
    0.14
    emek
    0.14
    evi
    0.14
    GMEM
    0.13
    CHANT
    0.13
    Act Density 0.006%

    No Known Activations