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

    Neuronpedia

    INDEX
    Explanations

    sequences of code or programming-related syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ;
    -0.56
     
    -0.54
     |
    -0.54
     por
    -0.53
    $
    -0.52
     “
    -0.51
     $
    -0.50
    <th>
    -0.50
    ja
    -0.50
    :
    -0.50
    POSITIVE LOGITS
     myſelf
    1.27
     itſelf
    1.21
    DockStyle
    1.19
     Theſe
    1.16
    ImageContext
    1.16
    ſelves
    1.15
     فريبيس
    1.14
     Anſ
    1.14
     reaſon
    1.13
    DeleteBehavior
    1.13
    Act Density 0.009%

    No Known Activations