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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and phrases indicating time or dates

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

    Follows punctuation like commas and periods

    np_acts-logits-general · gemini-2.0-flash

    commas followed by continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.07
     Majefty
    -1.03
     itſelf
    -1.02
     $_"
    -1.01
     Jefus
    -1.01
     Efq
    -0.99
     betweenstory
    -0.99
     становника
    -0.97
    Personensuche
    -0.97
    saraba
    -0.97
    POSITIVE LOGITS
     I
    0.85
    <eos>
    0.76
    I
    0.73
     we
    0.70
    ↵↵
    0.69
    .
    0.66
    ↵
    0.64
     it
    0.61
     (
    0.61
    The
    0.61
    Act Density 0.689%

    No Known Activations