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

    Neuronpedia

    INDEX
    Explanations

    words related to strength and power

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Correction
    -0.71
     Newly
    -0.70
     Sloan
    -0.70
    Hop
    -0.69
    oleon
    -0.68
     Hilton
    -0.68
     McCann
    -0.67
    ĸļ
    -0.66
    apolis
    -0.65
     Kare
    -0.65
    POSITIVE LOGITS
     enough
    1.00
    nesses
    0.98
    ener
    0.94
    enough
    0.94
     winds
    0.79
     contender
    0.78
     Enough
    0.78
     cryptography
    0.78
    man
    0.78
     handshake
    0.77
    Act Density 0.078%

    No Known Activations