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

    Neuronpedia

    INDEX
    Explanations

    indicators of function calls in a programming context

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

    programming code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     juſ
    -0.66
     betweenstory
    -0.63
     itſelf
    -0.63
     pleaſure
    -0.63
     ſch
    -0.61
     ſtate
    -0.61
     ſon
    -0.60
     myſelf
    -0.60
    abestanden
    -0.59
     diſt
    -0.59
    POSITIVE LOGITS
    ->
    1.37
    ]->
    1.09
    ()->
    1.05
    _->
    0.99
    ']->
    0.96
    ')->
    0.94
    )->
    0.91
    ])->
    0.86
    ))->
    0.85
    ")->
    0.85
    Act Density 0.013%

    No Known Activations