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

    Neuronpedia

    INDEX
    Explanations

    code and programming-related constructs, particularly focused on specific data structures or types

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.67
    ’
    -0.56
     always
    -0.56
    '
    -0.55
     E
    -0.53
     further
    -0.50
    حيان
    -0.50
    ,
    -0.50
     a
    -0.49
     no
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    1.11
     autorytatywna
    1.02
    MigrationBuilder
    1.02
    oredCriteria
    0.98
    writeFieldEnd
    0.97
     auffi
    0.91
     ―――――
    0.89
     myſelf
    0.85
    addCriterion
    0.84
    Parcelize
    0.84
    Act Density 0.255%

    No Known Activations