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

    Neuronpedia

    INDEX
    Explanations

    words related to accuracy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accurate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATA
    -0.78
    doms
    -0.75
    hov
    -0.75
    mere
    -0.73
    neys
    -0.72
    berries
    -0.71
    aden
    -0.71
    spl
    -0.71
    cheon
    -0.70
    Connector
    -0.70
    POSITIVE LOGITS
    uracy
    1.15
     accurate
    1.05
     inaccurate
    1.02
     portrayal
    1.02
     accuracy
    1.00
     inacc
    1.00
     depiction
    0.98
     representations
    0.90
     appraisal
    0.90
     depictions
    0.89
    Act Density 0.012%

    No Known Activations