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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "my" in various contexts related to personal experiences and possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.18
    ories
    -0.17
     unanim
    -0.15
    elder
    -0.14
    ź
    -0.14
    ensed
    -0.13
    atos
    -0.13
    mi
    -0.13
    nya
    -0.13
    umbs
    -0.13
    POSITIVE LOGITS
    riad
    0.36
    opic
    0.33
    rtle
    0.32
    anmar
    0.31
    opia
    0.30
    ri
    0.29
     myself
    0.28
    rrha
    0.27
    embros
    0.26
    /my
    0.23
    Act Density 0.146%

    No Known Activations