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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "we" and variations thereof that indicate collective experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ectors
    -0.15
     our
    -0.14
     intention
    -0.14
     lúc
    -0.14
     intentions
    -0.14
     Dav
    -0.14
    .Doc
    -0.14
    çIJ
    -0.14
    iffe
    -0.13
    ô
    -0.13
    POSITIVE LOGITS
     شاÙĩد
    0.17
    hear
    0.16
     Ori
    0.15
     seeing
    0.15
    loser
    0.15
    awei
    0.15
     Integral
    0.14
     expecting
    0.14
    ibold
    0.14
    ÅĻeh
    0.14
    Act Density 0.067%

    No Known Activations