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

    Neuronpedia

    INDEX
    Explanations

    references to gendered pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Biôgrafia
    -0.82
    PreferredItem
    -0.81
    UnsafeEnabled
    -0.74
     Roskov
    -0.71
    StoryboardSegue
    -0.69
    httphttps
    -0.66
    Hentet
    -0.65
    EndInit
    -0.65
    gameserver
    -0.65
    PreExecute
    -0.63
    POSITIVE LOGITS
     חיצוניים
    0.61
     she
    0.57
    she
    0.56
     zij
    0.54
    $__
    0.51
     dumne
    0.51
    himself
    0.51
    hers
    0.51
     She
    0.50
    ticoli
    0.49
    Act Density 0.216%

    No Known Activations