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

    Neuronpedia

    INDEX
    Explanations

    terms related to newness and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wap
    -0.16
    ki
    -0.14
    rv
    -0.14
     revolutions
    -0.14
    ota
    -0.13
     detail
    -0.13
    isl
    -0.13
     previous
    -0.13
    argas
    -0.13
     previously
    -0.13
    POSITIVE LOGITS
    swire
    0.21
    -found
    0.21
     regime
    0.19
    sworth
    0.18
    ystore
    0.17
    -old
    0.17
     arrang
    0.16
    -generation
    0.15
     arrangement
    0.15
    ypse
    0.15
    Act Density 0.099%

    No Known Activations