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

    Neuronpedia

    INDEX
    Explanations

    parentheses with numbers inside them

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     lull
    -0.75
     inund
    -0.74
     everyday
    -0.73
     retard
    -0.73
     intensive
    -0.73
     daily
    -0.72
     clin
    -0.71
     wre
    -0.71
     electr
    -0.70
     sav
    -0.69
    POSITIVE LOGITS
    sic
    1.68
    see
    1.54
    formerly
    1.54
    excluding
    1.54
    including
    1.52
    which
    1.51
    emphasis
    1.50
    also
    1.48
    aka
    1.48
    although
    1.48
    Act Density 1.112%

    No Known Activations