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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal belongings or possessions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ownership and possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.74
    vine
    -0.72
    ved
    -0.70
    zzle
    -0.67
     Unsure
    -0.64
     Originally
    -0.64
    rose
    -0.62
    shall
    -0.62
    een
    -0.60
    verb
    -0.60
    POSITIVE LOGITS
     sake
    1.66
     purposes
    1.30
     own
    1.24
     reasons
    1.05
     liking
    1.04
     sins
    0.95
     upcoming
    0.94
     constituents
    0.92
    ummies
    0.89
     purpose
    0.88
    Act Density 0.093%

    No Known Activations