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

    Neuronpedia

    INDEX
    Explanations

    quotations and descriptions from editorial movie reviews

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental concerns and their impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )."
    -0.75
    )</
    -0.67
    ?).
    -0.62
    )"
    -0.61
    !).
    -0.60
    ?)
    -0.60
     ?)
    -0.59
    ).[
    -0.58
    .")
    -0.58
    ?]
    -0.56
    POSITIVE LOGITS
    equality
    0.54
     Princ
    0.53
     undesirable
    0.49
     unprepared
    0.48
     sporting
    0.47
     unpopular
    0.46
    agame
    0.45
    agonists
    0.45
    gress
    0.45
     unrecogn
    0.44
    Act Density 2.704%

    No Known Activations