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

    Neuronpedia

    INDEX
    Explanations

    quantities or references to groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LEM
    -0.18
    Recognizer
    -0.16
    agne
    -0.14
     повин
    -0.14
    ieri
    -0.14
    nier
    -0.14
    ìĨĮëħĦ
    -0.14
    bourg
    -0.14
    andin
    -0.14
    eger
    -0.14
    POSITIVE LOGITS
     believe
    0.18
     think
    0.16
    oha
    0.15
    vern
    0.15
     Members
    0.15
     viewers
    0.15
     wonder
    0.14
    ras
    0.14
    elta
    0.14
     members
    0.14
    Act Density 0.100%

    No Known Activations