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

    Neuronpedia

    INDEX
    Explanations

    phrases related to categorization or listing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orian
    -0.14
    cht
    -0.14
    éĹ
    -0.14
    luet
    -0.13
    airs
    -0.13
    uckle
    -0.13
    uela
    -0.13
     Nullable
    -0.13
    AGES
    -0.13
     ger
    -0.13
    POSITIVE LOGITS
    elin
    0.17
    anna
    0.16
    æĤ£
    0.15
    rof
    0.15
    NCY
    0.14
     simp
    0.14
     informant
    0.14
    anter
    0.14
    SAM
    0.14
    apg
    0.14
    Act Density 0.001%

    No Known Activations