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

    Neuronpedia

    INDEX
    Explanations

    phrases related to counting and numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    óÅĤ
    -0.18
    ettings
    -0.15
    hooks
    -0.15
     váºŃy
    -0.15
    quential
    -0.15
    .wall
    -0.15
    /desktop
    -0.15
    kind
    -0.15
    udev
    -0.15
    eward
    -0.14
    POSITIVE LOGITS
    enance
    0.30
    erc
    0.17
    inue
    0.17
    جÙħ
    0.16
    /address
    0.16
    =count
    0.16
    /count
    0.16
    rophe
    0.16
    àµįà´
    0.15
    DownLatch
    0.15
    Act Density 0.045%

    No Known Activations