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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cauſe
    -1.09
     raiſ
    -1.05
     purpoſe
    -1.03
     houſe
    -1.01
     fevere
    -1.00
     uſed
    -1.00
     Racine
    -0.99
     pleaſure
    -0.98
     caufe
    -0.95
     Houſe
    -0.95
    POSITIVE LOGITS
     them
    1.20
     him
    1.06
     Them
    0.98
     THEM
    0.96
     Him
    0.95
    Them
    0.93
     HIM
    0.92
     us
    0.92
    Him
    0.91
    м
    0.82
    Act Density 0.127%

    No Known Activations