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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest a positive outcome or improvement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soever
    -0.77
    ér
    -0.66
    phia
    -0.66
    estic
    -0.66
    disabled
    -0.65
    ãĤ¢ãĥ«
    -0.64
    yss
    -0.63
     Practices
    -0.61
     Ples
    -0.60
     Technologies
    -0.60
    POSITIVE LOGITS
     interesting
    1.20
     entertaining
    1.11
     fascinating
    1.09
     intriguing
    1.07
     compelling
    1.06
     awkward
    1.03
     amusing
    0.98
     easier
    0.97
     enjoyable
    0.97
     excellent
    0.97
    Act Density 0.061%

    No Known Activations