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

    Neuronpedia

    INDEX
    Explanations

    code constructs and programming syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.81
    >*/
    -0.70
     */;
    -0.68
    حياته
    -0.67
    ')['
    -0.64
    )».
    -0.63
    __':
    -0.62
     Theſe
    -0.61
    $_.
    -0.61
    "){
    -0.61
    POSITIVE LOGITS
    ISupport
    0.57
     doch
    0.50
    ijen
    0.48
    AnchorStyles
    0.47
    hals
    0.47
    numerusform
    0.45
     sait
    0.45
    aughey
    0.44
    örung
    0.44
     defaultstate
    0.44
    Act Density 0.448%

    No Known Activations