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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the pronoun "we" and its variations, indicating a focus on collective actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odyn
    -0.16
     маÑĪ
    -0.14
    antino
    -0.14
    agu
    -0.14
     Coleman
    -0.14
     costing
    -0.14
    las
    -0.13
     wing
    -0.13
    elli
    -0.13
    oz
    -0.13
    POSITIVE LOGITS
    Å¡ak
    0.17
    ;\↵
    0.15
     arrest
    0.14
    Ø´ÙĪ
    0.14
    errick
    0.14
    adol
    0.14
    çīĩ
    0.14
    ãģıãĤī
    0.13
    433
    0.13
    ¡°
    0.13
    Act Density 0.279%

    No Known Activations