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

    Neuronpedia

    INDEX
    Explanations

    patterns related to events happening immediately one after another

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sequential events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kept
    -0.65
     unfocusedRange
    -0.65
    enberg
    -0.64
    oret
    -0.62
    oS
    -0.62
    utenberg
    -0.61
    oire
    -0.61
    acles
    -0.60
    Ble
    -0.60
    database
    -0.60
    POSITIVE LOGITS
    noon
    0.89
    aneously
    0.88
    ricular
    0.84
    imester
    0.80
     noon
    0.80
     midnight
    0.78
     graduation
    0.76
    enges
    0.76
     lunch
    0.73
    rely
    0.72
    Act Density 0.029%

    No Known Activations