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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uniqueness or singularity

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing individual roles or identities within a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mares
    -0.86
     whilst
    -0.73
     VIDEOS
    -0.68
    cies
    -0.68
    ibaba
    -0.67
    furt
    -0.67
    cation
    -0.66
    VERTISEMENT
    -0.65
     incorporates
    -0.65
    WAR
    -0.65
    POSITIVE LOGITS
     smartest
    1.18
     happiest
    1.15
     same
    1.09
     beneficiary
    1.04
     fastest
    1.04
     strongest
    1.03
     rightful
    1.01
     opposite
    1.01
     hottest
    1.00
     brunt
    1.00
    Act Density 0.153%

    No Known Activations