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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.83
     "
    -0.76
     “
    -0.75
    ↵↵
    -0.74
    boldmath
    -0.68
     
    -0.67
     للاسماء
    -0.65
     Lowe
    -0.63
     "..\..\..\
    -0.62
    )_
    -0.61
    POSITIVE LOGITS
     Cæsar
    1.05
    ChildScrollView
    0.95
     Efq
    0.92
     itſelf
    0.91
     Majefty
    0.91
     himſelf
    0.89
    DebuggerNonUser
    0.88
     Chriſt
    0.88
    HasForeignKey
    0.87
     AttributeSet
    0.86
    Act Density 1.480%

    No Known Activations