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

    Neuronpedia

    INDEX
    Explanations

    commands or requests to inform or share something with someone

    oai_token-act-pair · gpt-3.5-turbo

    commands or requests directed at an audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imposed
    -0.80
    adesh
    -0.75
    ItemTracker
    -0.68
    cells
    -0.67
    conservancy
    -0.65
    ccording
    -0.64
    served
    -0.64
    everal
    -0.63
    aband
    -0.63
     è£ıè¦ļéĨĴ
    -0.60
    POSITIVE LOGITS
    tale
    1.58
    ingly
    1.13
     us
    1.10
     lies
    1.02
     tales
    1.01
     stories
    0.97
     me
    0.95
     tale
    0.93
     Tale
    0.90
     jokes
    0.87
    Act Density 0.051%

    No Known Activations