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

    Neuronpedia

    INDEX
    Explanations

    mentions of private or privileged matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rers
    -0.74
    grass
    -0.73
     Ducks
    -0.70
    LER
    -0.67
     Ryder
    -0.66
     Shake
    -0.65
    ORN
    -0.65
    WAYS
    -0.64
    calling
    -0.63
    balls
    -0.62
    POSITIVE LOGITS
    ilege
    1.56
    ileged
    1.48
    ately
    1.19
    acies
    1.17
    atis
    1.01
    aband
    1.00
    ession
    0.99
    acy
    0.97
    atism
    0.96
    ility
    0.94
    Act Density 0.019%

    No Known Activations