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

    Neuronpedia

    INDEX
    Explanations

    references to surveys and research data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esson
    -0.15
    jÃł
    -0.15
    cke
    -0.15
    appa
    -0.14
    fits
    -0.14
    pek
    -0.14
    otti
    -0.13
    ohl
    -0.13
    ritt
    -0.13
    AZY
    -0.13
    POSITIVE LOGITS
     survey
    0.70
    survey
    0.62
     Survey
    0.60
     surveys
    0.59
     poll
    0.57
    Survey
    0.56
    _survey
    0.50
     surveyed
    0.47
    urvey
    0.47
    poll
    0.46
    Act Density 0.263%

    No Known Activations