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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blumenthal
    -0.70
    unker
    -0.70
     Hussein
    -0.69
     Mahm
    -0.68
     Ukrain
    -0.64
     Lerner
    -0.62
     Logged
    -0.61
     Huma
    -0.61
     Haf
    -0.59
     whereas
    -0.58
    POSITIVE LOGITS
     own
    1.62
     respective
    0.95
     OWN
    0.91
     Own
    0.89
     customary
    0.89
     usual
    0.88
    selves
    0.86
     stride
    0.85
     entire
    0.84
     hometown
    0.82
    Act Density 0.308%

    No Known Activations