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

    Neuronpedia

    INDEX
    Explanations

    references to death or dying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SSION
    -0.17
    íĺģ
    -0.15
    auses
    -0.15
    ntag
    -0.15
    darwin
    -0.14
    ldb
    -0.14
    olars
    -0.14
    credible
    -0.14
    orge
    -0.14
    ãĥ¡ãĥ³ãĥĪ
    -0.14
    POSITIVE LOGITS
    lier
    0.29
    bolt
    0.28
    locks
    0.28
    ening
    0.28
    locked
    0.28
    pan
    0.28
    beat
    0.28
    locking
    0.25
    weight
    0.25
    liest
    0.24
    Act Density 0.014%

    No Known Activations