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

    Neuronpedia

    INDEX
    Explanations

    discussions of actions related to relationships and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -END
    -0.16
    yar
    -0.16
    uell
    -0.15
    anan
    -0.15
    lut
    -0.15
    abbrev
    -0.15
     Mitar
    -0.15
    ired
    -0.14
     tup
    -0.13
    amat
    -0.13
    POSITIVE LOGITS
     fore
    0.18
    íĴ
    0.16
    ombine
    0.16
     ub
    0.16
    νη
    0.16
    izard
    0.15
    çİĩ
    0.15
     Od
    0.15
    efe
    0.15
    емон
    0.15
    Act Density 0.057%

    No Known Activations