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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentences or contexts that involve female subjects or pronouns, especially focusing on her actions, experiences, or attributes.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
     himself
    -1.05
    himself
    -0.93
     Himself
    -0.82
     koji
    -0.82
     који
    -0.74
    وفاته
    -0.69
    AndEndTag
    -0.66
     doInBackground
    -0.65
    łbym
    -0.63
    くん
    -0.63
    POSITIVE LOGITS
     herself
    1.73
    herself
    1.16
     she
    1.09
     her
    0.95
     bint
    0.89
     shes
    0.87
    حياتها
    0.86
     ihrem
    0.80
     actress
    0.79
     lesbian
    0.78
    Act Density 2.243%

    No Known Activations