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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical borders and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢоÑĩ
    -0.07
    ç´ł
    -0.06
    æ·
    -0.05
    inear
    -0.05
     dispose
    -0.05
    ancellable
    -0.05
     disposal
    -0.05
     hunt
    -0.05
     unp
    -0.05
    disposed
    -0.05
    POSITIVE LOGITS
     humanitarian
    0.09
    odyn
    0.08
    vik
    0.08
     permission
    0.07
    uki
    0.07
     delivery
    0.07
     deliveries
    0.07
    мп
    0.07
    ilters
    0.07
     PERMISSION
    0.07
    Act Density 0.011%

    No Known Activations