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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.16
    侯
    -0.15
    Units
    -0.15
    zej
    -0.14
     removeFrom
    -0.14
    &view
    -0.14
    ENDOR
    -0.14
     fatal
    -0.13
    099
    -0.13
    @brief
    -0.13
    POSITIVE LOGITS
     two
    0.25
     three
    0.24
     four
    0.21
     plus
    0.21
     six
    0.20
     countless
    0.19
    plus
    0.19
     one
    0.19
     five
    0.19
     several
    0.19
    Act Density 0.117%

    No Known Activations