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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intptr
    -0.70
    initState
    -0.68
    WriteBarrier
    -0.59
    љено
    -0.58
    awtextra
    -0.56
    tagHelperRunner
    -0.55
     TextInputType
    -0.55
    amse
    -0.54
    ioutil
    -0.53
    OrNil
    -0.52
    POSITIVE LOGITS
     للمعارف
    0.95
     nakalista
    0.79
     apologised
    0.57
     stabilisation
    0.54
    isation
    0.53
     scepticism
    0.52
     emphasised
    0.50
     maximise
    0.49
    "(
    0.48
     apologise
    0.48
    Act Density 0.056%

    No Known Activations