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

    Neuronpedia

    INDEX
    Explanations

    references to the word "All" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estone
    -0.17
    нен
    -0.15
    eling
    -0.15
    ascade
    -0.14
    central
    -0.14
    بÙĪر
    -0.14
     Cv
    -0.13
    less
    -0.13
    论
    -0.13
    /gtest
    -0.13
    POSITIVE LOGITS
    iances
    0.19
    igator
    0.18
    buquerque
    0.17
    iance
    0.16
    igators
    0.16
    compat
    0.15
    worm
    0.15
    itere
    0.15
    gro
    0.15
    otre
    0.15
    Act Density 0.067%

    No Known Activations