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

    Neuronpedia

    INDEX
    Explanations

    specific terms or words with a numerical value mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    jri
    -1.08
    âĹ¼
    -1.01
    iland
    -1.00
    CI
    -0.96
    aukee
    -0.96
    erker
    -0.95
    GoldMagikarp
    -0.92
    ulhu
    -0.92
    _-
    -0.91
    gaard
    -0.91
    POSITIVE LOGITS
     itself
    1.45
    ultimate
    1.11
     oneself
    1.06
     yourself
    1.00
     himself
    1.00
    lessness
    1.00
    icide
    0.99
     '
    0.99
    marked
    0.98
    mark
    0.94
    Act Density 0.698%

    No Known Activations