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

    Neuronpedia

    INDEX
    Explanations

    references to variables in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -1.33
     ―――――
    -0.98
    Jereo
    -0.96
    )";
    -0.85
     '\\;'
    -0.81
     saites
    -0.80
     myſelf
    -0.80
     --------------
    -0.80
     doubtnut
    -0.78
     itſelf
    -0.77
    POSITIVE LOGITS
     $
    1.45
    ($
    1.13
    ="{{$
    1.05
    [$
    0.96
    $
    0.96
    .$
    0.95
     ($
    0.94
    '][$
    0.92
     //$
    0.92
    ://$
    0.90
    Act Density 0.394%

    No Known Activations