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

    Neuronpedia

    INDEX
    Explanations

    symbolic representations or notations related to mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.82
     againſt
    -0.81
     ſeveral
    -0.76
     برانيه
    -0.71
    ſelves
    -0.69
     Jefus
    -0.68
     Chrift
    -0.68
     Chriftian
    -0.67
     utafitiHapana
    -0.67
     faſt
    -0.66
    POSITIVE LOGITS
     S
    1.85
     s
    1.67
    S
    1.30
     getS
    1.29
     س
    1.11
    getS
    1.07
     ST
    1.03
     SI
    1.03
     st
    0.99
    Ｓ
    0.99
    Act Density 0.552%

    No Known Activations