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

    Neuronpedia

    INDEX
    Explanations

    sentences that involve scientific experiments or processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.74
    andowski
    -0.64
    bidden
    -0.60
     skeletal
    -0.60
    ogenesis
    -0.60
    ensive
    -0.60
    ulin
    -0.59
    ilts
    -0.58
    arious
    -0.57
     transpired
    -0.57
    POSITIVE LOGITS
     yourself
    1.46
     yourselves
    1.38
     Yourself
    1.21
     preferably
    1.09
    cknow
    1.04
     wisely
    0.95
    ichever
    0.92
     responsibly
    0.91
     your
    0.87
     please
    0.84
    Act Density 2.686%

    No Known Activations