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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating preference or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eru
    -0.18
    essen
    -0.16
    azon
    -0.16
    616
    -0.15
    mun
    -0.14
    orf
    -0.14
     due
    -0.14
    ocities
    -0.14
    èŃľ
    -0.14
    lass
    -0.13
    POSITIVE LOGITS
     otherwise
    0.23
     ones
    0.23
     others
    0.22
     other
    0.22
     mere
    0.20
    otherwise
    0.19
     any
    0.19
     alternatives
    0.18
     actual
    0.17
     simply
    0.17
    Act Density 0.129%

    No Known Activations