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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to "Down" in various contexts, particularly relating to Down syndrome and associated individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andum
    -0.82
    aceous
    -0.81
    ¯¯¯¯
    -0.78
    ĸļ
    -0.74
    ================================
    -0.72
    olkien
    -0.70
    ature
    -0.69
    acca
    -0.69
    archives
    -0.69
    ============
    -0.68
    POSITIVE LOGITS
    stairs
    1.46
    hill
    1.10
    graded
    1.01
    ward
    0.89
    lap
    0.84
    river
    0.84
    grading
    0.83
    grades
    0.83
    edin
    0.80
    wind
    0.80
    Act Density 0.015%

    No Known Activations