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

    Neuronpedia

    INDEX
    Explanations

    phrases related to document publication or publicizing information

    oai_token-act-pair · gpt-3.5-turbo

    instances of publication or revelation of information, particularly in a political or news context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reproduction
    -0.61
     Bahá
    -0.58
     LH
    -0.57
     continuation
    -0.56
     LX
    -0.56
     POV
    -0.56
     Transactions
    -0.55
     americ
    -0.55
     placement
    -0.53
     ([
    -0.53
    POSITIVE LOGITS
     Thursday
    1.48
     Wednesday
    1.47
     Tuesday
    1.46
     Monday
    1.43
     Friday
    1.43
     yesterday
    1.43
     Saturday
    1.27
     Sunday
    1.23
    Thursday
    1.20
    Tuesday
    1.15
    Act Density 0.496%

    No Known Activations