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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ownership or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize individuality or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olic
    -0.78
     Dates
    -0.68
    oms
    -0.64
    anwhile
    -0.62
     incumbent
    -0.62
    onite
    -0.61
     Burgess
    -0.60
    mers
    -0.60
     Antar
    -0.58
     APPLIC
    -0.58
    POSITIVE LOGITS
     accord
    0.99
    Cloud
    0.89
     distinct
    0.74
    zig
    0.73
     Chronicles
    0.71
     unique
    0.71
    cloud
    0.68
     distinctive
    0.67
     separate
    0.65
    ãĤ¨ãĥ«
    0.65
    Act Density 0.034%

    No Known Activations