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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific span of time

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    minster
    -0.69
    found
    -0.67
    Materials
    -0.66
    otle
    -0.65
     Cosponsors
    -0.65
     torch
    -0.65
    andro
    -0.63
    Row
    -0.61
    fol
    -0.61
    usky
    -0.61
    POSITIVE LOGITS
     spanning
    0.90
    frames
    0.90
     periods
    0.84
    icals
    0.78
     lasting
    0.78
    iday
    0.77
     ending
    0.74
    icity
    0.73
     ranging
    0.73
     thereafter
    0.73
    Act Density 0.063%

    No Known Activations