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

    Neuronpedia

    INDEX
    Explanations

    conjunctions used in comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.88
     ―――――
    -0.86
    neſs
    -0.82
     Saltar
    -0.80
     Shakspeare
    -0.79
     Houſe
    -0.77
     raiſ
    -0.75
     uſed
    -0.75
     fubject
    -0.75
     themſelves
    -0.74
    POSITIVE LOGITS
     or
    1.28
     یا
    1.18
     Or
    1.16
     atau
    1.14
     OR
    1.13
     eller
    1.10
     oder
    1.07
    หรือ
    1.06
    or
    1.05
     vagy
    1.01
    Act Density 0.246%

    No Known Activations