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

    Neuronpedia

    INDEX
    Explanations

    function and method call patterns in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to scope or parenthesis

    np_acts-logits-general · gemini-2.0-flash

    => syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.71
     démocr
    -0.62
    }}}{\
    -0.58
     hâte
    -0.58
    !!</
    -0.58
    )}_
    -0.58
     mohair
    -0.57
     écout
    -0.57
    
    -0.57
     myſelf
    -0.57
    POSITIVE LOGITS
     =>
    1.71
    =>
    1.12
    =>$
    0.88
    Rightarrow
    0.87
     =>'
    0.82
    =>'
    0.78
     ->
    0.77
     <=
    0.77
     =>{
    0.75
    =>"
    0.74
    Act Density 0.077%

    No Known Activations