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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions happening concurrently with a specific time marker

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal pronouns and expressions of ongoing or past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occasion
    -0.75
     Cosponsors
    -0.74
    MpServer
    -0.74
    nexus
    -0.70
    ãĥ¼ãĥĨ
    -0.65
    ãĤ¨ãĥ«
    -0.65
     sooner
    -0.64
    EStream
    -0.61
     endpoint
    -0.61
     âĨij
    -0.60
    POSITIVE LOGITS
     await
    0.99
     waits
    0.94
     awaited
    0.94
     wait
    0.92
     awaits
    0.90
     waited
    0.86
     langu
    0.85
     sleeps
    0.83
     recovers
    0.82
     slept
    0.82
    Act Density 0.160%

    No Known Activations