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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to programming functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uttle
    -0.15
     Friedman
    -0.15
    ulty
    -0.14
    _COMPILE
    -0.14
    imson
    -0.14
     Ñģк
    -0.14
    iliate
    -0.14
    etu
    -0.13
    instanc
    -0.13
    onis
    -0.13
    POSITIVE LOGITS
     Fort
    0.24
     fort
    0.22
    Fort
    0.21
    fort
    0.21
    logical
    0.20
     subroutine
    0.19
    REW
    0.18
     logical
    0.17
     intent
    0.17
    intent
    0.17
    Act Density 0.032%

    No Known Activations