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

    Neuronpedia

    INDEX
    Explanations

    terms related to uninitiated or inexperienced individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    anwhile
    -0.82
    everal
    -0.70
     arrang
    -0.69
    igsaw
    -0.69
     skelet
    -0.65
    */(
    -0.64
     compr
    -0.64
    ornia
    -0.63
     heartbeat
    -0.62
     unlocks
    -0.62
    POSITIVE LOGITS
    structed
    1.21
    hibited
    1.15
    jured
    1.13
    formed
    1.07
    itial
    1.05
    cluded
    0.99
    apolis
    0.93
    flation
    0.93
    atural
    0.92
    fect
    0.91
    Act Density 6.555%

    No Known Activations