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

    Neuronpedia

    INDEX
    Explanations

    timestamps or time references within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of temporal markers related to the act of writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igham
    -0.73
     heck
    -0.68
     bandwagon
    -0.67
     impe
    -0.66
     sacrific
    -0.65
     streng
    -0.64
     disob
    -0.64
    ogie
    -0.63
    benefit
    -0.63
     Cosponsors
    -0.61
    POSITIVE LOGITS
    cember
    0.72
    info
    0.71
     redacted
    0.70
    ctl
    0.69
     estimates
    0.65
     estimate
    0.64
    oth
    0.62
    rox
    0.61
    uary
    0.61
     Updated
    0.61
    Act Density 0.066%

    No Known Activations