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

    Neuronpedia

    INDEX
    Explanations

    dates and events that mark important milestones

    oai_token-act-pair · gpt-3.5-turbo

    mentions of anniversaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manip
    -0.68
     Mono
    -0.66
    isp
    -0.63
     Load
    -0.63
    Table
    -0.61
     manip
    -0.61
    Flow
    -0.60
     maneu
    -0.60
     manipulation
    -0.60
     Mode
    -0.59
    POSITIVE LOGITS
     anniversary
    4.09
     Anniversary
    2.91
    iversary
    2.38
     birthday
    1.76
     commem
    1.63
     Birthday
    1.43
     commemor
    1.40
    enary
    1.34
     commemorate
    1.26
     milestone
    1.20
    Act Density 0.011%

    No Known Activations