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

    Neuronpedia

    INDEX
    Explanations

    instances of the words "this" and "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enos
    -0.15
    azes
    -0.15
    enan
    -0.15
    اÙĤØ©
    -0.15
    oyal
    -0.14
    loub
    -0.14
    86
    -0.14
     behalf
    -0.13
     Ballard
    -0.13
    AGES
    -0.13
    POSITIVE LOGITS
     happened
    0.16
    mtx
    0.15
    oro
    0.15
     Incontri
    0.14
    coma
    0.14
     plá
    0.14
     Ùħات
    0.14
     is
    0.14
    ipple
    0.13
    phere
    0.13
    Act Density 0.129%

    No Known Activations