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

    Neuronpedia

    INDEX
    Explanations

    legal terms and statutes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Seasons
    -1.03
     Indigo
    -0.99
    rane
    -0.97
    ¿½
    -0.94
    intosh
    -0.93
    ONSORED
    -0.89
     Dy
    -0.89
     RIS
    -0.89
     Stafford
    -0.89
     cereal
    -0.88
    POSITIVE LOGITS
    istically
    1.85
    utory
    1.73
    ements
    1.67
    uary
    1.49
    istical
    1.46
    ues
    1.45
    utor
    1.36
    utes
    1.34
    uously
    1.29
    amation
    1.27
    Act Density 1.025%

    No Known Activations