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

    Neuronpedia

    INDEX
    Explanations

    terms 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
    inki
    -0.74
    #$#$
    -0.73
    AIN
    -0.72
    loo
    -0.71
    osphere
    -0.71
    doms
    -0.71
    hedon
    -0.71
     Pharma
    -0.69
    hov
    -0.69
    acid
    -0.69
    POSITIVE LOGITS
     portrayal
    1.08
     depiction
    1.03
    uracy
    0.99
     representation
    0.90
     reproduction
    0.88
     appraisal
    0.87
     depictions
    0.87
     description
    0.85
     accuracy
    0.83
    imates
    0.82
    Act Density 0.054%

    No Known Activations