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

    Neuronpedia

    INDEX
    Explanations

    personal possessive pronouns followed by possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual's work or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.95
    needed
    -0.82
    microsoft
    -0.80
    jury
    -0.79
    uve
    -0.73
    urers
    -0.72
    ATA
    -0.72
    obe
    -0.69
    livion
    -0.69
    ibraries
    -0.69
    POSITIVE LOGITS
     antics
    1.22
     penchant
    1.14
     adventures
    1.09
     hilarious
    1.03
     backstory
    1.03
     thoughts
    1.03
     adorable
    1.02
     newest
    1.00
     latest
    0.99
     tweets
    0.98
    Act Density 0.260%

    No Known Activations