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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    time and date information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebin
    -0.82
     blackmail
    -0.79
     faked
    -0.76
     superiors
    -0.76
     artificially
    -0.75
     notor
    -0.74
     trusts
    -0.73
     overloaded
    -0.73
     causation
    -0.71
     cannabin
    -0.71
    POSITIVE LOGITS
     TBA
    1.37
    noon
    1.33
     Doors
    1.24
     TBD
    1.23
     noon
    1.19
     Dinner
    1.19
     Lunch
    1.13
     Noon
    1.12
    Saturday
    1.12
     Tickets
    1.10
    Act Density 0.190%

    No Known Activations