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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being above a certain level or standard

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Deal
    -0.69
    NV
    -0.68
    ãĤ¹ãĥĪ
    -0.65
    OVER
    -0.63
    ument
    -0.63
    Creat
    -0.61
    DAY
    -0.61
    NetMessage
    -0.61
    alloc
    -0.59
    cycles
    -0.59
    POSITIVE LOGITS
    ground
    1.49
    mentioned
    1.18
     ground
    1.13
     average
    0.96
    average
    0.90
     sea
    0.86
     freezing
    0.83
     Ground
    0.83
     Average
    0.82
     decks
    0.79
    Act Density 0.054%

    No Known Activations