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

    Neuronpedia

    INDEX
    Explanations

    timestamps or date formats in a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertising
    -0.93
     telev
    -0.89
    interstitial
    -0.86
    Bey
    -0.79
     Cosby
    -0.78
     Paula
    -0.77
    ansas
    -0.77
     television
    -0.76
     Beyon
    -0.75
     Burnett
    -0.74
    POSITIVE LOGITS
     GitHub
    1.35
     github
    1.32
     FreeBSD
    1.25
     Github
    1.23
     linux
    1.22
     GNU
    1.19
     RFC
    1.18
     systemd
    1.16
     Linux
    1.16
     deprecated
    1.15
    Act Density 1.006%

    No Known Activations