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

    Neuronpedia

    INDEX
    Explanations

    references to subplots in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.32
    ups
    -0.27
    scription
    -0.24
    ify
    -0.24
    ably
    -0.23
    ulative
    -0.22
    house
    -0.21
    t
    -0.21
    uptools
    -0.19
    ogonal
    -0.19
    POSITIVE LOGITS
    ordinated
    0.24
    ordinates
    0.21
    stract
    0.20
    woo
    0.20
    redits
    0.20
    mers
    0.19
    suming
    0.19
    terr
    0.18
    redit
    0.17
    tel
    0.17
    Act Density 0.010%

    No Known Activations