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

    Neuronpedia

    INDEX
    Explanations

    references to critical or impactful societal events and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    line
    -0.45
    ored
    -0.24
    imuth
    -0.21
    adecimal
    -0.21
    LINE
    -0.21
    htub
    -0.20
    ground
    -0.20
    down
    -0.20
    ewidth
    -0.20
    ulace
    -0.20
    POSITIVE LOGITS
    wards
    0.17
    ory
    0.17
    ORY
    0.17
    PHA
    0.16
     Pes
    0.15
    ursion
    0.14
     Teeth
    0.14
     Baron
    0.14
    396
    0.14
    atters
    0.14
    Act Density 0.151%

    No Known Activations