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

    Neuronpedia

    INDEX
    Explanations

    references to the opinions and behaviors of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gio
    -0.15
    ayne
    -0.15
    PÅĻi
    -0.14
    icap
    -0.14
    ickey
    -0.13
    tsy
    -0.13
    rang
    -0.13
    ROOM
    -0.13
     Clip
    -0.13
    itemap
    -0.13
    POSITIVE LOGITS
    oir
    0.16
    lt
    0.15
    Pair
    0.14
    ÏĮ
    0.14
    orca
    0.14
    LEG
    0.14
    ober
    0.14
    igned
    0.13
    erdale
    0.13
     kolem
    0.13
    Act Density 0.104%

    No Known Activations