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

    Neuronpedia

    INDEX
    Explanations

    pronouns, particularly those referring to male and female subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.99
    Datuak
    -0.94
    contentLoaded
    -0.92
     Theſe
    -0.89
    Aholisi
    -0.87
    حياتها
    -0.86
    GEBURTS
    -0.85
     itſelf
    -0.84
     pinulongan
    -0.83
     Jefus
    -0.81
    POSITIVE LOGITS
     said
    0.76
    said
    0.51
     dijo
    0.51
    he
    0.48
     doInBackground
    0.47
    Shaw
    0.46
     he
    0.45
     Said
    0.44
    Said
    0.44
     сказал
    0.43
    Act Density 0.050%

    No Known Activations