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

    Neuronpedia

    INDEX
    Explanations

    closing braces and structure-related syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     –
    -0.56
     +
    -0.55
     (
    -0.54
    .
    -0.53
     A
    -0.50
    ,
    -0.50
    ="+
    -0.46
     >
    -0.46
     "
    -0.46
     V
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    1.34
     itſelf
    1.26
     myſelf
    1.20
    RectangleBorder
    1.16
     purpoſe
    1.16
     NSCoder
    1.15
     uſe
    1.08
     ſche
    1.08
     Theſe
    1.08
     houſe
    1.05
    Act Density 0.297%

    No Known Activations