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

    Neuronpedia

    INDEX
    Explanations

    comparisons of intensity or frequency

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "more than ever."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.76
    ename
    -0.76
    ochet
    -0.70
    ouri
    -0.68
    dor
    -0.66
    uliffe
    -0.65
     [&
    -0.65
    umbn
    -0.65
    okin
    -0.65
    tein
    -0.64
    POSITIVE LOGITS
     before
    0.94
     existed
    0.86
     BEFORE
    0.83
     dreamed
    0.81
     depended
    0.77
     imagined
    0.76
     imaginable
    0.74
    WHERE
    0.74
    before
    0.73
     recorded
    0.71
    Act Density 0.012%

    No Known Activations