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

    Neuronpedia

    INDEX
    Explanations

    terms related to detailed categorization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    од
    -0.15
    ureka
    -0.14
    lig
    -0.14
     handjob
    -0.14
    rowned
    -0.13
    омен
    -0.13
    ľ
    -0.13
    ê¸ī
    -0.13
     Bernard
    -0.13
     Kane
    -0.13
    POSITIVE LOGITS
    ansa
    0.16
    ource
    0.14
     Overse
    0.14
    ppard
    0.14
     annum
    0.14
    avin
    0.13
     еди
    0.13
     intptr
    0.13
    æ£
    0.13
     overse
    0.13
    Act Density 0.027%

    No Known Activations