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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and other structural elements within the text

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

    Punctuation marks at the start of a line

    np_acts-logits-general · gemini-2.0-flash

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لينك
    -0.74
     purpoſe
    -0.70
     ་་
    -0.66
     ſtate
    -0.65
     استنادى
    -0.65
     Alcott
    -0.65
     myſelf
    -0.64
     Syndicate
    -0.64
     Gaul
    -0.64
    )_/¯
    -0.63
    POSITIVE LOGITS
     don
    0.47
    URIComponent
    0.47
     in
    0.47
     viewDidLoad
    0.47
     A
    0.46
     it
    0.46
     
    0.45
    InjectAttribute
    0.45
     form
    0.41
     års
    0.40
    Act Density 0.141%

    No Known Activations