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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hens
    -0.70
    untu
    -0.56
    bench
    -0.56
    gow
    -0.55
    mar
    -0.55
    ifts
    -0.55
    elected
    -0.54
    liquid
    -0.53
    lett
    -0.53
    ose
    -0.53
    POSITIVE LOGITS
     same
    0.99
     phenomenon
    0.98
     latter
    0.94
     topic
    0.86
    .<
    0.78
    .[
    0.78
     trope
    0.78
     matter
    0.77
    FTWARE
    0.77
    MSN
    0.75
    Act Density 1.036%

    No Known Activations