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

    Neuronpedia

    INDEX
    Explanations

    names of rankings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rankings and the term "files."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggie
    -0.72
    opic
    -0.70
    gal
    -0.69
     buddies
    -0.69
    outhern
    -0.69
     reinforcement
    -0.69
    WC
    -0.67
     ECO
    -0.65
     dear
    -0.64
     Timber
    -0.64
    POSITIVE LOGITS
     Rankings
    1.93
     ISS
    1.72
    Files
    1.45
     churn
    1.30
    ÙĨ
    1.26
    stakes
    1.26
    Iss
    0.95
     Iss
    0.94
    qi
    0.94
    generated
    0.91
    Act Density 0.063%

    No Known Activations