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

    Neuronpedia

    INDEX
    Explanations

    references to statistics and quantifiable data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uld
    -0.15
    ignet
    -0.15
    веÑī
    -0.15
    ught
    -0.14
    osta
    -0.14
    ceae
    -0.14
    ea
    -0.14
    efault
    -0.14
    loe
    -0.14
    ureka
    -0.13
    POSITIVE LOGITS
    eras
    0.15
    ugas
    0.15
    αιο
    0.14
    _Action
    0.14
     Kimber
    0.13
    813
    0.13
    embre
    0.13
    à¸ķรว
    0.13
    ÙĬدا
    0.13
     Meh
    0.13
    Act Density 0.218%

    No Known Activations