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

    Neuronpedia

    INDEX
    Explanations

    first-person singular pronouns and related verbs indicating personal experiences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     our
    -0.83
     ourselves
    -0.83
     we
    -0.68
     Our
    -0.67
    Our
    -0.65
     nossos
    -0.55
    我们的
    -0.55
     OUR
    -0.54
     nossas
    -0.53
    our
    -0.52
    POSITIVE LOGITS
     myſelf
    0.79
     himſelf
    0.78
    himself
    0.75
     himself
    0.74
    ագրություններ
    0.74
    bootstrapcdn
    0.72
     насељу
    0.72
    UnsafeEnabled
    0.71
    таратура
    0.70
     Савезне
    0.69
    Act Density 0.283%

    No Known Activations