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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases, particularly ones denoting a shorter time duration

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hran
    -0.88
    olitan
    -0.86
    ieri
    -0.83
    alogy
    -0.81
    olis
    -0.79
    itiz
    -0.77
    odium
    -0.74
    ulet
    -0.73
    iom
    -0.72
    ilon
    -0.72
    POSITIVE LOGITS
     half
    0.87
     halfway
    0.79
     stellar
    0.78
     cents
    0.76
     expected
    0.75
     satisfactory
    0.72
     ideal
    0.71
    ½
    0.70
     ½
    0.69
    capacity
    0.69
    Act Density 10.608%

    No Known Activations