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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "We" and other plural first-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     al
    -0.17
    inn
    -0.17
     Al
    -0.15
    maker
    -0.15
     makers
    -0.15
    alin
    -0.15
    Al
    -0.15
    410
    -0.14
    makers
    -0.14
    AJ
    -0.14
    POSITIVE LOGITS
    rum
    0.17
    .Void
    0.16
    urer
    0.15
    ÑijÑĢ
    0.15
    ityEngine
    0.15
    âĸį
    0.14
    .BorderFactory
    0.14
    fuse
    0.14
    squeeze
    0.14
     {{--<
    0.14
    Act Density 0.048%

    No Known Activations