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

    Neuronpedia

    INDEX
    Explanations

    words related to conditional dependency and causality in discussions of policies or procedural changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pur
    -0.15
     Pon
    -0.15
    ilib
    -0.14
    guide
    -0.14
    urma
    -0.14
    scriptions
    -0.14
    sth
    -0.14
     GUIDE
    -0.14
    #echo
    -0.14
    км
    -0.14
    POSITIVE LOGITS
    orp
    0.15
    án
    0.14
    .openg
    0.14
    agnost
    0.14
    emaker
    0.14
    bb
    0.13
     differential
    0.13
    'ÑĶ
    0.13
     opening
    0.13
    BB
    0.13
    Act Density 0.002%

    No Known Activations