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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to gaming experiences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eor
    -0.69
     interven
    -0.69
    iti
    -0.66
    iates
    -0.65
     occas
    -0.64
    opted
    -0.60
    igr
    -0.60
    throp
    -0.59
    stan
    -0.58
    stad
    -0.57
    POSITIVE LOGITS
     namely
    0.86
     undoubtedly
    0.85
    \\\\\\\\
    0.74
    assis
    0.73
     simplicity
    0.73
    KEN
    0.70
     simply
    0.68
    KER
    0.67
    ovie
    0.66
     probably
    0.66
    Act Density 1.953%

    No Known Activations