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

    Neuronpedia

    INDEX
    Explanations

    file names or technical specifications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     veter
    -0.87
    lies
    -0.84
     advoc
    -0.79
     quir
    -0.78
     perspect
    -0.74
     mathemat
    -0.72
     pse
    -0.70
     tremend
    -0.70
    ptive
    -0.68
     policymakers
    -0.68
    POSITIVE LOGITS
     Otherwise
    0.99
     Later
    0.98
     Secondly
    0.94
     Lastly
    0.93
     Afterwards
    0.93
     Alternatively
    0.92
    done
    0.91
     Likewise
    0.91
     Converted
    0.91
     Anyway
    0.89
    Act Density 0.057%

    No Known Activations