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

    Neuronpedia

    INDEX
    Explanations

    dates and time markers

    oai_token-act-pair · gpt-3.5-turbo

    the word "until" and its variations indicating future events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aque
    -0.78
    pour
    -0.76
    ãĤ«
    -0.71
    MU
    -0.70
    cult
    -0.69
    nic
    -0.67
    path
    -0.67
    Ability
    -0.67
    isible
    -0.67
    VP
    -0.66
    POSITIVE LOGITS
     AFTER
    0.82
    hower
    0.78
    hetti
    0.74
    ulic
    0.73
     msec
    0.71
    terday
    0.69
     Ago
    0.68
    itures
    0.67
     hindsight
    0.67
     Til
    0.66
    Act Density 0.030%

    No Known Activations