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

    Neuronpedia

    INDEX
    Explanations

    terms related to peace and conflict resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lage
    -0.16
    mos
    -0.15
    luž
    -0.15
    raquo
    -0.15
    imson
    -0.15
    lah
    -0.14
    neo
    -0.14
    ederland
    -0.14
    edo
    -0.14
    Supply
    -0.14
    POSITIVE LOGITS
    keeping
    0.33
    ful
    0.29
    ably
    0.29
    able
    0.28
    fully
    0.27
    keepers
    0.27
    FUL
    0.27
    fulness
    0.26
    keeper
    0.26
    full
    0.26
    Act Density 0.016%

    No Known Activations