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

    Neuronpedia

    INDEX
    Explanations

    numbers and units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    specific references to labeled items or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tyr
    -0.74
     skelet
    -0.65
     guiName
    -0.58
     seiz
    -0.55
     blat
    -0.54
     suspic
    -0.53
     actionGroup
    -0.51
     reven
    -0.51
     agre
    -0.50
     surv
    -0.50
    POSITIVE LOGITS
    ).
    2.36
    )."
    2.20
    .).
    2.14
    )!
    2.09
    ),"
    2.06
    !).
    1.93
    ),
    1.93
    )?
    1.92
    %).
    1.91
    )—
    1.91
    Act Density 0.328%

    No Known Activations