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

    Neuronpedia

    INDEX
    Explanations

    statistical percentages and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.66
    XtraBars
    -0.65
     &
    -0.61
    RepeatedField
    -0.60
     coté
    -0.56
    tabak
    -0.51
     ३
    -0.51
     daß
    -0.51
     inggris
    -0.48
     २
    -0.48
    POSITIVE LOGITS
     five
    1.31
     eight
    1.29
     seven
    1.26
     six
    1.24
     nine
    1.22
     four
    1.21
     three
    1.07
    five
    1.03
    six
    0.99
    four
    0.97
    Act Density 0.461%

    No Known Activations