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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and other punctuation indicating speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ostavi
    -0.60
    AndEndTag
    -0.57
     ujednoznacz
    -0.52
    EndContext
    -0.51
     ProgressDialog
    -0.47
    ".
    -0.46
     aDecoder
    -0.45
    ').
    -0.44
    UnitTesting
    -0.44
     étrangères
    -0.43
    POSITIVE LOGITS
    Datuak
    0.83
    himu
    0.69
    LabelTagHelper
    0.68
    bibfield
    0.68
     whoſe
    0.64
    drawal
    0.63
     насељу
    0.60
    ſelves
    0.60
    ackerel
    0.59
    reversible
    0.58
    Act Density 0.473%

    No Known Activations