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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to political affiliations and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urt
    -0.17
    baugh
    -0.17
    asp
    -0.17
    eÅŁ
    -0.15
    ander
    -0.15
    adel
    -0.14
    isen
    -0.14
    isses
    -0.14
     Jacqu
    -0.14
    alara
    -0.14
    POSITIVE LOGITS
    ariant
    0.15
    alyze
    0.15
    ubl
    0.15
     compens
    0.14
     camel
    0.14
    ayment
    0.14
    è³ĩ
    0.13
     Fem
    0.13
     mandate
    0.13
    apper
    0.13
    Act Density 0.270%

    No Known Activations