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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical quantities and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëł¥
    -0.15
    623
    -0.15
    é¦Ĩ
    -0.14
     prohib
    -0.14
    óc
    -0.14
     Siz
    -0.14
    atta
    -0.14
     Catal
    -0.14
    аÑĢÑĩ
    -0.14
    943
    -0.14
    POSITIVE LOGITS
     Sür
    0.16
    Ùħز
    0.16
    áºł
    0.15
    eldorf
    0.15
    uchos
    0.14
    ¹Ħ
    0.14
    ยà¸ĩ
    0.14
    okens
    0.14
    ụy
    0.14
    yang
    0.14
    Act Density 0.112%

    No Known Activations