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

    Neuronpedia

    INDEX
    Explanations

    occurrences of possessive forms or contractions involving "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nels
    -0.89
    xual
    -0.86
    ality
    -0.80
    rade
    -0.80
    irement
    -0.76
    CHAT
    -0.76
    VP
    -0.74
    nel
    -0.72
    vik
    -0.71
    ees
    -0.71
    POSITIVE LOGITS
     largest
    1.23
     richest
    1.11
     fastest
    1.08
     wealthiest
    1.05
     deadliest
    1.02
     poorest
    1.01
     tallest
    1.01
     biggest
    0.99
     finest
    0.98
     hottest
    0.98
    Act Density 0.040%

    No Known Activations