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

    Neuronpedia

    INDEX
    Explanations

    references to heat-related concepts and natural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oha
    -0.18
    orney
    -0.15
    breaker
    -0.14
    573
    -0.14
    unami
    -0.13
    åħ¥ãĤĬ
    -0.13
    oltage
    -0.13
    437
    -0.13
    ibo
    -0.13
    ailles
    -0.13
    POSITIVE LOGITS
     sp
    0.53
     releasing
    0.43
     release
    0.41
     spit
    0.41
     emit
    0.40
     output
    0.39
     releases
    0.38
     spat
    0.36
     produce
    0.36
     producing
    0.35
    Act Density 0.284%

    No Known Activations