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

    Neuronpedia

    INDEX
    Explanations

    references to peace and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nger
    -0.17
    raquo
    -0.16
    so
    -0.16
    maz
    -0.15
    ederland
    -0.15
    neo
    -0.15
    sein
    -0.15
    redd
    -0.14
    luž
    -0.14
    mos
    -0.14
    POSITIVE LOGITS
    keeping
    0.32
    ably
    0.30
    ful
    0.30
    able
    0.29
    fully
    0.28
    FUL
    0.28
    fulness
    0.26
    eful
    0.26
    full
    0.26
    keepers
    0.25
    Act Density 0.016%

    No Known Activations