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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency within the text

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

    mild negative intensifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.71
     ſind
    -0.68
     يتيمه
    -0.67
     שוליים
    -0.60
     Italijani
    -0.60
    MigrationBuilder
    -0.59
    AutoModerator
    -0.59
     itſelf
    -0.59
     EconPapers
    -0.58
     Numerade
    -0.56
    POSITIVE LOGITS
     fuckin
    0.58
     goddamn
    0.58
     kinda
    0.56
     shitty
    0.56
     crappy
    0.54
     dunno
    0.53
     fucking
    0.52
     messed
    0.50
     fuck
    0.49
     heck
    0.48
    Act Density 0.184%

    No Known Activations