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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating an increase or enhancement compared to previous levels

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "than ever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ename
    -0.75
    atchewan
    -0.72
     Cosponsors
    -0.71
    oute
    -0.70
    onal
    -0.69
     [&
    -0.69
    kefeller
    -0.67
    dor
    -0.67
    umbn
    -0.67
     Beir
    -0.67
    POSITIVE LOGITS
     before
    0.99
     BEFORE
    0.87
     dreamed
    0.83
     existed
    0.82
     imaginable
    0.79
    before
    0.79
     imagined
    0.76
     recorded
    0.75
     alive
    0.74
    WHERE
    0.71
    Act Density 0.017%

    No Known Activations