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

    Neuronpedia

    INDEX
    Explanations

    commas and punctuation marks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -1.10
    tvguidetime
    -0.99
    rungsseite
    -0.93
     lenker
    -0.93
    verwijspagina
    -0.92
    GEBURTSDATUM
    -0.92
     تانيه
    -0.91
    AddTagHelper
    -0.90
     kaarangay
    -0.90
    -0.87
    POSITIVE LOGITS
     the
    0.88
     we
    0.86
     it
    0.85
     there
    0.75
     this
    0.72
     you
    0.69
     when
    0.67
     I
    0.67
     if
    0.66
    由于
    0.61
    Act Density 0.460%

    No Known Activations