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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and related expressions of ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ested
    -0.79
    vier
    -0.76
    hari
    -0.70
    edin
    -0.69
    ved
    -0.64
    endif
    -0.64
    orama
    -0.64
    etheless
    -0.62
    glers
    -0.60
    venants
    -0.59
    POSITIVE LOGITS
     sake
    1.66
     purposes
    1.19
     own
    0.98
     upcoming
    0.93
     birthday
    0.92
     sins
    0.90
     amusement
    0.81
     respective
    0.81
     troubles
    0.80
     sanity
    0.80
    Act Density 0.076%

    No Known Activations