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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific point in time or event triggering an action

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lly
    -0.89
    alus
    -0.76
    since
    -0.76
    ãĥĦ
    -0.73
    orate
    -0.72
     since
    -0.71
     understatement
    -0.71
    ply
    -0.70
    fusc
    -0.70
     nonetheless
    -0.70
    POSITIVE LOGITS
     dust
    1.15
     doors
    1.12
     timer
    1.12
     tide
    1.08
     curtain
    1.06
     rains
    1.04
     opportunity
    1.03
     sun
    1.02
     lights
    1.00
     deadline
    0.97
    Act Density 0.212%

    No Known Activations