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

    Neuronpedia

    INDEX
    Explanations

    references to control systems or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oud
    -0.16
    que
    -0.15
    azzi
    -0.14
    croft
    -0.14
     stabil
    -0.14
    ice
    -0.14
    ITO
    -0.14
    ne
    -0.14
    amus
    -0.13
    ocracy
    -0.13
    POSITIVE LOGITS
    FFE
    0.16
    Mixin
    0.14
    rep
    0.14
    aryawan
    0.14
    ÑĢÑĥз
    0.14
    zier
    0.14
    yz
    0.14
    ummings
    0.13
    NewLabel
    0.13
     seins
    0.13
    Act Density 0.003%

    No Known Activations