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

    Neuronpedia

    INDEX
    Explanations

    titles and references to well-known dystopian literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ì´Į
    -0.16
    _PATCH
    -0.15
    unan
    -0.15
    362
    -0.15
    501
    -0.15
    482
    -0.14
    arith
    -0.14
    廳
    -0.14
    602
    -0.14
     trench
    -0.13
    POSITIVE LOGITS
     dyst
    0.23
     Hand
    0.23
    /command
    0.18
    Hand
    0.18
     Hulu
    0.18
     Commander
    0.18
     ut
    0.17
    sponsor
    0.17
     reproductive
    0.17
    wives
    0.16
    Act Density 0.012%

    No Known Activations