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

    Neuronpedia

    INDEX
    Explanations

    numeric data and technical terms related to configurations and calculations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.10
    uga
    -1.00
    hner
    -1.00
    aye
    -0.98
    ¾
    -0.97
    orio
    -0.97
    lio
    -0.97
    ogi
    -0.95
    liam
    -0.94
     tink
    -0.93
    POSITIVE LOGITS
     Borders
    0.96
     Recap
    0.96
    Ops
    0.96
     Blend
    0.95
     WARRANT
    0.92
     Investigation
    0.92
     Investigators
    0.92
     Exactly
    0.91
    _.
    0.91
     Detection
    0.91
    Act Density 0.358%

    No Known Activations