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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lifting or removing restrictions and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    	Copyright
    -0.18
     коп
    -0.16
    527
    -0.16
    ipse
    -0.16
    inne
    -0.15
    Ñĸж
    -0.15
    iliz
    -0.15
    767
    -0.14
    ìĹ°
    -0.14
    ury
    -0.14
    POSITIVE LOGITS
    wald
    0.18
    oped
    0.16
    ruba
    0.15
    ighton
    0.15
     Giov
    0.14
     Gund
    0.14
    wire
    0.14
    enable
    0.14
    ĵį
    0.14
    leck
    0.14
    Act Density 0.195%

    No Known Activations