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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotations or cited statements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reel
    -0.81
     accomp
    -0.76
     Versus
    -0.73
     fray
    -0.70
     roar
    -0.69
     square
    -0.69
     draw
    -0.68
     rolled
    -0.67
     metic
    -0.67
     guide
    -0.66
    POSITIVE LOGITS
    there
    2.10
    they
    1.93
    these
    1.83
    everyone
    1.80
    we
    1.76
    nob
    1.73
    this
    1.72
    it
    1.71
    many
    1.70
    everything
    1.69
    Act Density 0.273%

    No Known Activations