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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advis
    -0.78
     confidentiality
    -0.68
     stewards
    -0.68
     budgets
    -0.64
     chopping
    -0.64
     roam
    -0.64
     imposition
    -0.62
     leap
    -0.62
     execution
    -0.62
     waterfall
    -0.61
    POSITIVE LOGITS
    E
    0.97
    Va
    0.95
    J
    0.94
    O
    0.93
    A
    0.91
    S
    0.86
    Skill
    0.85
    Crew
    0.85
    AX
    0.84
    L
    0.84
    Act Density 0.074%

    No Known Activations