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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to various topics including environmental issues, legal matters, community projects, historical events, and technical developments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     "$:/
    -0.70
     Wim
    -0.69
     Koen
    -0.66
    20439
    -0.64
    Merit
    -0.64
    mble
    -0.64
     largeDownload
    -0.63
     Kessler
    -0.62
    ////////////////
    -0.62
     Slot
    -0.59
    POSITIVE LOGITS
    alian
    0.76
     herself
    0.62
    pedia
    0.61
    owner
    0.61
     autonomy
    0.60
     lobby
    0.59
     lover
    0.58
     harmed
    0.58
     himself
    0.57
     anonym
    0.57
    Act Density 2.800%

    No Known Activations