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

    Neuronpedia

    INDEX
    Explanations

    references to mistakes or inaccuracies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edom
    -0.79
    tsky
    -0.78
    ILA
    -0.76
    gdala
    -0.72
    apy
    -0.72
    nai
    -0.72
    rises
    -0.71
    amen
    -0.67
    electric
    -0.67
    estine
    -0.66
    POSITIVE LOGITS
    uracy
    0.88
     margin
    0.87
    ously
    0.85
     corrected
    0.79
    fully
    0.79
     dece
    0.77
     corrections
    0.77
     error
    0.75
     perpetrated
    0.75
     correction
    0.74
    Act Density 0.013%

    No Known Activations