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

    Neuronpedia

    INDEX
    Explanations

    letters 'Ċ' followed by numbers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     frontline
    -0.81
     ones
    -0.76
     freel
    -0.75
     spitting
    -0.72
     racing
    -0.72
     encomp
    -0.72
     spir
    -0.71
     casc
    -0.70
     suff
    -0.69
     reb
    -0.69
    POSITIVE LOGITS
    RAW
    1.79
    Rated
    1.55
    advertisement
    1.53
    Advertisement
    1.44
    Advertisements
    1.41
    Trivia
    1.41
    SOURCE
    1.39
    Loading
    1.39
    Reviewer
    1.36
    Topics
    1.36
    Act Density 0.402%

    No Known Activations