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

    Neuronpedia

    INDEX
    Explanations

    prompts asking the reader to verify that they are not a robot

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    76561
    -0.71
    itar
    -0.67
     Poc
    -0.63
     Sapp
    -0.60
     Brun
    -0.59
     Bethesda
    -0.59
     Brist
    -0.59
    talk
    -0.58
    ARC
    -0.57
     Carib
    -0.57
    POSITIVE LOGITS
     verify
    0.90
    asse
    0.78
    %]
    0.76
     enable
    0.73
     Subscribe
    0.72
     arming
    0.69
    ete
    0.67
     Sign
    0.66
     SIGN
    0.64
     subscribe
    0.63
    Act Density 0.011%

    No Known Activations