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

    Neuronpedia

    INDEX
    Explanations

    statements or facts regarded as accurate

    oai_token-act-pair · gpt-3.5-turbo

    statements related to accuracy and precision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.80
    acid
    -0.79
    AIN
    -0.75
    ovan
    -0.73
    doms
    -0.71
    Aid
    -0.71
    inki
    -0.71
    ATA
    -0.70
     Parties
    -0.70
    joining
    -0.69
    POSITIVE LOGITS
    uracy
    1.16
     portrayal
    1.00
     inacc
    0.97
     inaccurate
    0.92
     accuracy
    0.92
     depiction
    0.89
     appraisal
    0.87
    imates
    0.84
     inaccur
    0.83
    inately
    0.81
    Act Density 0.019%

    No Known Activations