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

    Neuronpedia

    INDEX
    Explanations

    references to news and news-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ex
    -0.16
    unya
    -0.16
    ext
    -0.16
    iggs
    -0.15
    toolbox
    -0.15
    ude
    -0.15
    utton
    -0.15
    ality
    -0.14
    etics
    -0.14
    ci
    -0.14
    POSITIVE LOGITS
    letters
    0.26
    room
    0.24
    flash
    0.22
    reader
    0.20
    feed
    0.20
    lett
    0.19
    stand
    0.18
    rp
    0.18
    stands
    0.18
    ROOM
    0.17
    Act Density 0.039%

    No Known Activations