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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to formal announcements and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.74
    ":"/
    -0.66
     WATCHED
    -0.60
    respective
    -0.59
    ealous
    -0.58
    peat
    -0.58
     imitate
    -0.57
    Export
    -0.57
    esides
    -0.57
    âĶĢâĶĢâĶĢâĶĢ
    -0.56
    POSITIVE LOGITS
     Wednesday
    1.95
     Tuesday
    1.94
     Thursday
    1.91
     Monday
    1.88
     Friday
    1.86
     yesterday
    1.76
     Saturday
    1.71
     Sunday
    1.67
    Thursday
    1.57
    Wednesday
    1.55
    Act Density 0.564%

    No Known Activations