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

    Neuronpedia

    INDEX
    Explanations

    phrases related to surveillance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "surprise" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hetti
    -0.72
     tense
    -0.69
    naires
    -0.67
     numbering
    -0.62
     Unch
    -0.60
    opathy
    -0.60
    YC
    -0.60
    itsch
    -0.60
     sender
    -0.59
     amber
    -0.59
    POSITIVE LOGITS
    geon
    1.39
    rounded
    1.28
    geons
    1.28
    round
    1.13
    render
    1.11
    fing
    1.10
    vey
    1.10
    prise
    1.09
    prising
    1.09
    prises
    1.02
    Act Density 0.023%

    No Known Activations