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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, particularly female characters and their personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     she
    -1.45
    she
    -1.27
     her
    -1.09
     herself
    -1.07
    She
    -1.05
    Она
    -1.04
    เธอ
    -1.04
    她
    -1.03
     вона
    -0.96
     ją
    -0.93
    POSITIVE LOGITS
     his
    1.28
    his
    1.05
     seine
    0.90
     njego
    0.89
     His
    0.84
    providedIn
    0.84
     HIS
    0.83
    ioutil
    0.82
     seiner
    0.82
     their
    0.81
    Act Density 0.153%

    No Known Activations