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

    Neuronpedia

    INDEX
    Explanations

    comparative words indicating a preference or superiority in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĩÛĮ
    -0.15
    arken
    -0.14
    gin
    -0.14
    861
    -0.14
    amp
    -0.13
    aget
    -0.13
    Mob
    -0.13
    141
    -0.13
    utz
    -0.13
    antwort
    -0.13
    POSITIVE LOGITS
     ones
    0.21
     necessarily
    0.20
     اÛĮÙĨÚ©Ùĩ
    0.19
     merely
    0.18
     being
    0.18
     usual
    0.17
    being
    0.15
    jis
    0.15
     just
    0.15
     relying
    0.14
    Act Density 0.023%

    No Known Activations