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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and systems infrastructure

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ynes
    -0.75
     pse
    -0.67
     nailed
    -0.66
    entimes
    -0.66
    anwhile
    -0.66
    reon
    -0.65
    hovah
    -0.64
    uggest
    -0.64
    aditional
    -0.64
     kneeling
    -0.63
    POSITIVE LOGITS
    cation
    0.86
    00
    0.82
    âĸĪâĸĪâĸĪâĸĪ
    0.80
    âĸĪâĸĪ
    0.78
    INFO
    0.76
    840
    0.75
    1969
    0.74
    08
    0.72
    007
    0.72
    864
    0.71
    Act Density 12.627%

    No Known Activations