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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     raiſ
    -1.08
     Dreyfus
    -1.05
     uſed
    -1.02
     cauſe
    -1.01
     purpoſe
    -1.01
     poffe
    -0.98
     ſtate
    -0.96
     Weyl
    -0.95
     Athenian
    -0.94
     houſe
    -0.94
    POSITIVE LOGITS
     them
    0.88
     HIM
    0.87
     him
    0.85
     THEM
    0.84
    Them
    0.84
    м
    0.83
     Them
    0.81
    Him
    0.80
     Him
    0.80
    m
    0.76
    Act Density 0.073%

    No Known Activations