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

    Neuronpedia

    INDEX
    Explanations

    references to various political positions and leadership titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BRACKET
    -0.55
    toHaveBeenCalled
    -0.52
    atikan
    -0.51
    HEIM
    -0.49
    pumpe
    -0.49
    iligen
    -0.48
    intérêt
    -0.48
    AxisSize
    -0.47
    conversions
    -0.47
    ləş
    -0.46
    POSITIVE LOGITS
     emeritus
    0.96
     designate
    0.90
    alty
    0.88
    hips
    0.87
     Emeritus
    0.84
     elect
    0.84
    Elect
    0.82
    elect
    0.79
    SHIP
    0.77
    AsUp
    0.75
    Act Density 0.273%

    No Known Activations