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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to equations and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    echan
    -0.15
    á»ĩn
    -0.14
    olec
    -0.14
    tributes
    -0.14
    aida
    -0.14
    Ñģклад
    -0.14
    yen
    -0.13
    amu
    -0.13
    setDisplay
    -0.13
    SCII
    -0.13
    POSITIVE LOGITS
     represent
    0.43
     represents
    0.42
    表示
    0.41
    代表
    0.38
     representing
    0.38
    represent
    0.37
     indicates
    0.37
     indicating
    0.35
     indicate
    0.35
     Represents
    0.32
    Act Density 0.358%

    No Known Activations