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

    Neuronpedia

    INDEX
    Explanations

    discussions about decisions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lesia
    -0.20
    iera
    -0.15
    onde
    -0.14
    rew
    -0.14
    ustom
    -0.14
    ewed
    -0.14
    ekk
    -0.14
     tooth
    -0.14
    ëĭ¹
    -0.14
     balloon
    -0.13
    POSITIVE LOGITS
    isme
    0.18
    hai
    0.16
    avou
    0.15
    afort
    0.15
    à¤ĸ
    0.14
     DISCLAIM
    0.14
    Ł³
    0.14
    peare
    0.14
    çݯ
    0.14
    zcze
    0.14
    Act Density 0.289%

    No Known Activations