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

    Neuronpedia

    INDEX
    Explanations

    time intervals or ranges between different points in time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of time-related phrases and specific numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.62
    onite
    -0.60
    ŃĶ
    -0.59
     Nightmares
    -0.56
    AFTA
    -0.56
    yet
    -0.56
     Anonymous
    -0.55
     redes
    -0.55
     unfocusedRange
    -0.54
     Cube
    -0.54
    POSITIVE LOGITS
    flush
    0.70
     ])
    0.69
    ties
    0.68
     sexes
    0.64
    姫
    0.63
    aer
    0.63
    ]+
    0.59
    isp
    0.58
    doms
    0.58
     extremes
    0.58
    Act Density 0.124%

    No Known Activations