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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time or scheduling

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.90
    emort
    -0.80
    essee
    -0.77
    ategory
    -0.75
    negie
    -0.74
    egal
    -0.73
    hett
    -0.71
    ancies
    -0.70
    oice
    -0.69
    iability
    -0.68
    POSITIVE LOGITS
    dream
    1.60
    lights
    1.06
    care
    1.06
    light
    1.00
    long
    0.97
    break
    0.93
    nings
    0.89
    trip
    0.86
    glass
    0.85
    night
    0.84
    Act Density 1.322%

    No Known Activations