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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods leading up to significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vill
    -0.68
    aren
    -0.68
    atic
    -0.68
    drivers
    -0.68
    ENG
    -0.67
    Offline
    -0.67
    cn
    -0.66
    are
    -0.66
    tw
    -0.66
    ktop
    -0.65
    POSITIVE LOGITS
     sunrise
    0.84
     sunset
    0.73
     expiration
    0.71
     embark
    0.70
     Christmas
    0.68
    omore
    0.68
     Election
    0.68
     noon
    0.67
     fading
    0.66
     adulthood
    0.66
    Act Density 0.040%

    No Known Activations