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

    Neuronpedia

    INDEX
    Explanations

    references to "them" or "him" indicating a focus on relationships or interactions with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.63
     juſ
    -0.62
     pleaſure
    -0.61
     Diſ
    -0.59
     auroit
    -0.56
     Majefty
    -0.54
    panto
    -0.54
     becauſe
    -0.54
     anſ
    -0.53
     loue
    -0.53
    POSITIVE LOGITS
     them
    1.70
    them
    1.36
     Them
    1.33
    Them
    1.30
     THEM
    1.23
     him
    0.98
     us
    0.86
     них
    0.84
     eux
    0.77
    Him
    0.77
    Act Density 0.092%

    No Known Activations