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

    Neuronpedia

    INDEX
    Explanations

    complex sentence structures that involve actions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     her
    -1.03
    她的
    -0.93
     hennes
    -0.88
    herself
    -0.84
    彼女の
    -0.84
     suaminya
    -0.84
     hendes
    -0.81
     herself
    -0.79
    them
    -0.77
     ihn
    -0.73
    POSITIVE LOGITS
     she
    1.91
     она
    0.66
     zij
    0.60
     hän
    0.57
     היא
    0.49
     they
    0.48
    tagHelperRunner
    0.48
     sie
    0.47
    KEYCODE
    0.45
    ها
    0.45
    Act Density 0.208%

    No Known Activations