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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to people, particularly in the context of interactions or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -1.17
     Houſe
    -1.10
     cauſe
    -1.09
     Athenian
    -1.05
     raiſ
    -1.05
     Charlemagne
    -1.04
     pleaſure
    -1.04
     purpoſe
    -1.03
    ytale
    -1.03
     Weyl
    -1.00
    POSITIVE LOGITS
     us
    0.97
     them
    0.82
    us
    0.82
    self
    0.80
     him
    0.79
     Him
    0.76
    ness
    0.75
    </em>
    0.74
     as
    0.74
     Jim
    0.74
    Act Density 0.090%

    No Known Activations