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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that end with a punctuation mark, specifically a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.74
     advis
    -0.71
     reliability
    -0.71
     inactive
    -0.70
     situational
    -0.69
     lookout
    -0.69
     consistency
    -0.68
     flexibility
    -0.68
     caves
    -0.68
     contact
    -0.67
    POSITIVE LOGITS
    Amid
    1.15
    Yet
    1.13
     Amid
    1.11
     Though
    1.06
    Born
    1.06
     Yet
    1.05
     Ahead
    1.01
     Featuring
    0.99
     Despite
    0.99
    Hundreds
    0.99
    Act Density 0.472%

    No Known Activations