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

    Neuronpedia

    INDEX
    Explanations

    keywords related to accuracy and precision

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accuracy and precision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AIN
    -0.81
    loo
    -0.80
    acid
    -0.79
    doms
    -0.72
     Parties
    -0.71
    inki
    -0.71
     Pharma
    -0.71
    oly
    -0.69
    #$#$
    -0.69
    Aid
    -0.68
    POSITIVE LOGITS
    uracy
    1.09
     portrayal
    1.00
     depiction
    0.90
     appraisal
    0.88
     inacc
    0.85
     inaccurate
    0.85
     accuracy
    0.83
    imates
    0.82
    imated
    0.81
     depictions
    0.81
    Act Density 0.025%

    No Known Activations