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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases such as durations and specific periods

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    erella
    -0.75
     srfAttach
    -0.66
    angan
    -0.65
     Controls
    -0.62
    ashtra
    -0.62
    rawdownloadcloneembedreportprint
    -0.61
    igham
    -0.60
    vale
    -0.59
    erville
    -0.58
    acus
    -0.58
    POSITIVE LOGITS
     installments
    0.97
     years
    0.89
     weeks
    0.89
     iterations
    0.87
     generations
    0.86
    teenth
    0.86
     months
    0.85
    encies
    0.83
     millennium
    0.83
     decades
    0.82
    Act Density 4.785%

    No Known Activations