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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate parts of a whole or components of a larger concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    975
    -0.17
    dy
    -0.16
    rint
    -0.16
    ye
    -0.15
    dings
    -0.14
    ima
    -0.14
    .ide
    -0.14
    dir
    -0.14
    lah
    -0.14
    ics
    -0.14
    POSITIVE LOGITS
    iture
    0.16
    ake
    0.15
    /full
    0.14
     cul
    0.14
    _codegen
    0.14
    PickerController
    0.14
    .attrib
    0.13
    аÑĤегоÑĢ
    0.13
    align
    0.13
    atown
    0.13
    Act Density 0.048%

    No Known Activations