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

    Neuronpedia

    INDEX
    Explanations

    numeric values, especially related to financial or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gupta
    -0.16
     bur
    -0.15
     Tut
    -0.14
    cliffe
    -0.14
     Gale
    -0.14
     Hed
    -0.14
     Zak
    -0.14
     Jamie
    -0.14
    nothrow
    -0.14
    phet
    -0.14
    POSITIVE LOGITS
    86
    0.68
    861
    0.54
    866
    0.53
    863
    0.52
    864
    0.52
    862
    0.52
    865
    0.52
    860
    0.52
    868
    0.51
    87
    0.48
    Act Density 0.029%

    No Known Activations