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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals in a conversational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NASL
    -0.67
     Emerson
    -0.64
     Wellington
    -0.64
     unspecified
    -0.63
     Hercules
    -0.63
     Pegasus
    -0.62
     Forth
    -0.61
     Weston
    -0.61
     Darwin
    -0.59
     JFK
    -0.58
    POSITIVE LOGITS
    âĢ
    1.82
    »
    1.57
    «
    1.51
    ÃĥÃĤ
    1.47
    </
    1.44
    âľ
    1.44
    âĺ
    1.44
    îĢ
    1.43
    **
    1.43
    âĶ
    1.43
    Act Density 0.560%

    No Known Activations