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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns and information like grade levels and ages

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Throne
    -0.69
     Canaver
    -0.65
    ichick
    -0.64
     Warranty
    -0.64
     Taxi
    -0.63
    thy
    -0.62
    lyak
    -0.60
     monarchy
    -0.60
    ablishment
    -0.60
    sth
    -0.59
    POSITIVE LOGITS
     school
    1.53
     kindergarten
    1.53
     students
    1.48
    Students
    1.47
    school
    1.47
    School
    1.43
     classmates
    1.39
     kids
    1.34
     Students
    1.34
     School
    1.33
    Act Density 0.598%

    No Known Activations