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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political matters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eteenth
    -0.81
    OND
    -0.78
    HAM
    -0.76
    STON
    -0.72
    rities
    -0.72
    orne
    -0.71
    resa
    -0.70
    oen
    -0.69
    OPA
    -0.67
    arna
    -0.67
    POSITIVE LOGITS
     bore
    0.73
     behaved
    0.71
     redef
    0.69
     assum
    0.68
     could
    0.67
     wrest
    0.67
     proceeded
    0.67
     insin
    0.67
     resembled
    0.65
     constitute
    0.64
    Act Density 0.270%

    No Known Activations