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

    Neuronpedia

    INDEX
    Explanations

    dates or periods of time

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal relationships, specifically events occurring before a specified time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    are
    -0.77
    aren
    -0.72
    SA
    -0.72
    CAN
    -0.69
    DC
    -0.67
     Cipher
    -0.67
    Si
    -0.66
    atic
    -0.65
    Offline
    -0.65
    cn
    -0.64
    POSITIVE LOGITS
     sunset
    0.85
    lier
    0.81
     sunrise
    0.80
     noon
    0.80
     Christmas
    0.77
     expiration
    0.76
     halftime
    0.76
     Thanksgiving
    0.75
    noon
    0.74
     retracted
    0.73
    Act Density 0.042%

    No Known Activations