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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¸
    -0.15
    peria
    -0.15
    indow
    -0.15
     ***!↵
    -0.15
    oldem
    -0.14
    ãģĦãģĦ
    -0.14
    ิà¸ģาร
    -0.14
     Giang
    -0.13
    jejer
    -0.13
    imitives
    -0.13
    POSITIVE LOGITS
    }{
    0.36
     than
    0.27
    }{$
    0.20
     THAN
    0.19
     }
    0.18
     Than
    0.18
    than
    0.18
    )
    0.18
    §
    0.17
    )}
    0.17
    Act Density 0.064%

    No Known Activations