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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantity or number classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    殿
    -0.15
     Vig
    -0.15
    egie
    -0.15
    æļ®
    -0.14
     sever
    -0.14
    баÑĩ
    -0.14
    riday
    -0.14
    endon
    -0.14
     Osc
    -0.14
    ibble
    -0.14
    POSITIVE LOGITS
    isiyle
    0.16
    iek
    0.14
    rene
    0.14
    ese
    0.14
    ifetime
    0.14
    ãĤĩãģĨ
    0.14
    kaç
    0.13
    ÛĮزÛĮ
    0.13
    風
    0.13
    ãĥ¼ãĥĸ
    0.13
    Act Density 0.006%

    No Known Activations