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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.17
     пÑĥÑĤем
    -0.17
    ulaire
    -0.15
    nr
    -0.14
    ÑĪиÑģÑĮ
    -0.14
    enga
    -0.14
    å¼Ħ
    -0.14
     tÃŃmto
    -0.14
     CircularProgress
    -0.13
     pomocÃŃ
    -0.13
    POSITIVE LOGITS
    /us
    0.17
     many
    0.16
     lot
    0.14
    873
    0.14
     apart
    0.14
    adows
    0.14
    bidden
    0.14
     plenty
    0.14
     Eagle
    0.14
     overall
    0.13
    Act Density 0.108%

    No Known Activations