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

    Neuronpedia

    INDEX
    Explanations

    promotional terms and names related to events or products

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.78
    SEE
    -0.77
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
     Palmer
    -0.64
     Albion
    -0.64
    Lago
    -0.62
     Wolves
    -0.60
     needles
    -0.60
    MORE
    -0.60
     redundant
    -0.60
    POSITIVE LOGITS
    otions
    1.55
    otional
    1.50
    etheus
    1.47
    inent
    1.35
    inently
    1.34
    otion
    1.31
    inence
    1.26
    ises
    1.25
    oter
    1.25
    oting
    1.20
    Act Density 0.014%

    No Known Activations