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

    Neuronpedia

    INDEX
    Explanations

    superlatives indicating extremes or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives and adverbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammed
    -0.70
    ceive
    -0.70
    create
    -0.68
    anism
    -0.68
    attery
    -0.67
    azard
    -0.66
    tnc
    -0.66
     doorstep
    -0.62
    poke
    -0.61
    their
    -0.61
    POSITIVE LOGITS
    quickShipAvailable
    0.96
     downside
    0.89
     drawback
    0.82
     reason
    0.78
     question
    0.78
     caveat
    0.75
     notable
    0.72
     straw
    0.71
     exception
    0.70
     flaw
    0.70
    Act Density 0.216%

    No Known Activations