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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names and locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    picking
    -0.39
    wcsstore
    -0.39
     Clicker
    -0.38
    rings
    -0.37
    expr
    -0.36
    frames
    -0.35
    ergy
    -0.34
    rant
    -0.34
     ancest
    -0.33
    LOCK
    -0.33
    POSITIVE LOGITS
    ño
    0.49
    iffe
    0.47
    onga
    0.47
     Tesla
    0.46
    BILITY
    0.45
    asca
    0.45
    osal
    0.44
    BILITIES
    0.43
    zzi
    0.43
    otes
    0.42
    Act Density 9.659%

    No Known Activations