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

    Neuronpedia

    INDEX
    Explanations

    superlatives or rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to important entities or items, particularly in counts or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apon
    -0.71
    Dialogue
    -0.71
    ombs
    -0.70
    naires
    -0.69
    mares
    -0.69
    auer
    -0.68
    APD
    -0.67
    ourt
    -0.66
    yle
    -0.65
    ukong
    -0.65
    POSITIVE LOGITS
     easiest
    1.33
     biggest
    1.29
     closest
    1.25
     hardest
    1.24
     heaviest
    1.24
     frontrunner
    1.23
     cheapest
    1.23
     fastest
    1.21
     safest
    1.20
     weakest
    1.19
    Act Density 0.148%

    No Known Activations