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

    Neuronpedia

    INDEX
    Explanations

    references to specific people or titles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Digital
    -0.55
    ãĥł
    -0.53
    ISION
    -0.53
    apter
    -0.52
    Ocean
    -0.51
     Sussex
    -0.50
     Eleven
    -0.50
     Activision
    -0.50
    Org
    -0.49
    alogue
    -0.49
    POSITIVE LOGITS
    enhagen
    0.84
    istani
    0.82
    rats
    0.79
     Gork
    0.69
    allery
    0.63
    milo
    0.62
    enei
    0.62
    ocity
    0.60
    atown
    0.59
     guiActiveUn
    0.58
    Act Density 0.834%

    No Known Activations