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

    Neuronpedia

    INDEX
    Explanations

    a call to action to engage with content or share it

    oai_token-act-pair · gpt-3.5-turbo

    interactions and engagements related to online content sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     env
    -0.63
     Galile
    -0.59
     Mirage
    -0.56
     kidnapping
    -0.56
     robbery
    -0.55
     Siem
    -0.54
     Shining
    -0.54
     Gunn
    -0.54
     discriminating
    -0.54
     arming
    -0.53
    POSITIVE LOGITS
     archive
    1.06
     blogs
    1.04
     reader
    1.04
     bookmark
    1.03
    archive
    1.02
     Readers
    1.01
     RSS
    1.00
     archives
    1.00
     archived
    0.99
     blog
    0.99
    Act Density 0.993%

    No Known Activations