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

    Neuronpedia

    INDEX
    Explanations

    contacts or locations for communication purposes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     nurs
    -0.70
     subp
    -0.70
     mortg
    -0.69
    ulators
    -0.65
     Bermuda
    -0.62
    ibrary
    -0.59
     Trials
    -0.58
    cakes
    -0.58
     presentation
    -0.58
     decorations
    -0.57
    POSITIVE LOGITS
    ioned
    0.69
    =-=-
    0.69
    zbek
    0.68
     Toll
    0.67
    =-=-=-=-
    0.67
    Contact
    0.66
    ateful
    0.66
    OTOS
    0.65
    idays
    0.65
    UTH
    0.64
    Act Density 5.867%

    No Known Activations