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

    Neuronpedia

    INDEX
    Explanations

    information related to investigative journalism, fact-checking, and public accountability efforts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ulla
    -0.55
     Sabha
    -0.55
    yip
    -0.52
     reluct
    -0.48
    nown
    -0.47
    ridor
    -0.45
    phrine
    -0.45
    nings
    -0.44
     pose
    -0.43
    Jar
    -0.43
    POSITIVE LOGITS
     topics
    0.49
     subjects
    0.45
     UFOs
    0.45
     corruption
    0.43
    inas
    0.43
     Integrity
    0.43
     crime
    0.43
     unsolved
    0.42
     Unc
    0.42
     journalism
    0.41
    Act Density 13.560%

    No Known Activations