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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases ending in a period

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     advis
    -0.76
     advoc
    -0.75
     activ
    -0.74
     sal
    -0.72
     docks
    -0.68
     rall
    -0.67
     tyr
    -0.67
     aw
    -0.67
     comm
    -0.66
     overdue
    -0.64
    POSITIVE LOGITS
     Instead
    1.92
     Nor
    1.71
     Rather
    1.61
     Neither
    1.53
    Instead
    1.52
     Nonetheless
    1.37
     Nevertheless
    1.36
     nor
    1.35
    Nor
    1.31
     Quite
    1.28
    Act Density 0.475%

    No Known Activations