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

    Neuronpedia

    INDEX
    Explanations

    statistical percentages and their changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĨت
    -0.16
    den
    -0.15
    lap
    -0.14
    lady
    -0.14
     GANG
    -0.14
    laps
    -0.13
    odb
    -0.13
    OrUpdate
    -0.13
     ÑĨен
    -0.13
    opp
    -0.13
    POSITIVE LOGITS
    ile
    0.26
    iles
    0.25
    ìĶ©
    0.18
    ILES
    0.18
    tile
    0.17
     stake
    0.17
     of
    0.16
    å·¦åı³
    0.15
    èĤ¡ä»½
    0.15
    ILE
    0.15
    Act Density 0.072%

    No Known Activations