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

    Neuronpedia

    INDEX
    Explanations

    specific time references

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    1000
    -0.68
    advertisement
    -0.63
    ac
    -0.62
    2000
    -0.61
    ype
    -0.61
    bite
    -0.61
    eye
    -0.61
    Sounds
    -0.60
    unch
    -0.60
    1007
    -0.60
    POSITIVE LOGITS
    soever
    1.03
    upon
    0.73
     they
    0.71
    irlf
    0.70
     faced
    0.68
     temperatures
    0.68
    abouts
    0.66
     transitioning
    0.62
     astronauts
    0.61
     floods
    0.60
    Act Density 0.053%

    No Known Activations