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

    Neuronpedia

    INDEX
    Explanations

    historical or recent events and controversies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Release
    -0.53
     Skydragon
    -0.51
     ****
    -0.49
    peace
    -0.48
    ioxid
    -0.48
    verning
    -0.47
    rotein
    -0.47
    ooming
    -0.46
    osis
    -0.46
     Quantity
    -0.46
    POSITIVE LOGITS
     nor
    0.66
     shenan
    0.54
     precedent
    0.54
     controversial
    0.53
     censorship
    0.52
     contentious
    0.51
    pmwiki
    0.51
     advers
    0.50
     adversary
    0.50
    ILLE
    0.49
    Act Density 14.458%

    No Known Activations