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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" and related forms indicating collective action or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .cx
    -0.15
    etus
    -0.15
     Butt
    -0.14
    stal
    -0.14
    asse
    -0.14
    emiz
    -0.14
    upuncture
    -0.14
    zz
    -0.14
    bjerg
    -0.14
    ass
    -0.13
    POSITIVE LOGITS
     believe
    0.21
     estimate
    0.18
    zes
    0.17
     Believe
    0.16
     view
    0.16
    ivo
    0.15
    -bel
    0.15
    ÑĢоз
    0.15
     believes
    0.15
    bel
    0.15
    Act Density 0.091%

    No Known Activations