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

    Neuronpedia

    INDEX
    Explanations

    references to defining or explaining conditions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peror
    -0.16
    è¿Ļæĺ¯
    -0.15
    uliar
    -0.14
    enis
    -0.14
    ä½ĵ
    -0.13
    uche
    -0.13
    ï¼Į请
    -0.13
    ians
    -0.13
    Å©ng
    -0.13
    .cls
    -0.13
    POSITIVE LOGITS
     if
    0.37
     when
    0.36
    If
    0.33
     If
    0.33
     wenn
    0.31
    when
    0.30
     once
    0.29
    å¦Ĥæŀľ
    0.28
     When
    0.28
    When
    0.28
    Act Density 0.307%

    No Known Activations