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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific terms related to different events, places, and names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     gloss
    -0.73
    rium
    -0.68
    ERSON
    -0.63
    riched
    -0.63
    racuse
    -0.62
    ailability
    -0.60
    nect
    -0.60
    win
    -0.59
     glim
    -0.59
    ahime
    -0.58
    POSITIVE LOGITS
    restling
    0.82
    backer
    0.81
    kefeller
    0.77
     Bicycle
    0.75
    boat
    0.75
     Racer
    0.74
    IGH
    0.70
     Against
    0.70
    issance
    0.66
     Passenger
    0.66
    Act Density 10.414%

    No Known Activations