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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oner
    -0.75
    nuts
    -0.72
    ced
    -0.69
    EMS
    -0.67
    estern
    -0.66
    yrus
    -0.65
    luck
    -0.65
    kus
    -0.64
    avis
    -0.64
    roads
    -0.64
    POSITIVE LOGITS
     description
    0.85
     thereof
    0.82
    ript
    0.79
     descriptions
    0.76
     synopsis
    0.74
     wording
    0.74
     aloud
    0.72
    TextColor
    0.71
     describing
    0.70
    Description
    0.70
    Act Density 0.035%

    No Known Activations