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

    Neuronpedia

    INDEX
    Explanations

    references to technical terms related to technology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    obook
    -0.62
    named
    -0.62
    pired
    -0.60
    wrote
    -0.58
    actionDate
    -0.58
    pires
    -0.57
    iece
    -0.55
     Canaver
    -0.54
    rower
    -0.54
    ename
    -0.52
    POSITIVE LOGITS
    +.
    1.08
    *.
    0.89
    _.
    0.88
    's
    0.86
    ().
    0.84
    %.
    0.84
    .</
    0.83
    '.
    0.83
     sensibilities
    0.82
    .'
    0.81
    Act Density 0.709%

    No Known Activations