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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by possessive nouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and associated possessive phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.76
    ested
    -0.69
    zzle
    -0.65
    ved
    -0.65
    hari
    -0.64
    een
    -0.63
    vine
    -0.63
    shall
    -0.62
    vertisements
    -0.61
    ahead
    -0.60
    POSITIVE LOGITS
     sake
    1.74
     purposes
    1.31
     own
    1.26
     sins
    1.05
     reasons
    1.04
     upcoming
    0.91
     liking
    0.91
    ummies
    0.90
     constituents
    0.90
     sanity
    0.84
    Act Density 0.085%

    No Known Activations