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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ")->
    -0.55
    endsection
    -0.52
    DrawerLayout
    -0.52
    ]+=
    -0.51
     Riproduzione
    -0.51
    
    -0.50
     henvisninger
    -0.49
    unyai
    -0.48
    Przypisy
    -0.48
     typelib
    -0.47
    POSITIVE LOGITS
     myself
    1.73
     Myself
    1.49
    myself
    1.45
    我
    1.29
     me
    1.26
     ourselves
    1.25
    Myself
    1.24
     أنا
    1.21
    أنا
    1.19
     я
    1.18
    Act Density 0.101%

    No Known Activations