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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases or patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Judah
    -0.74
     Wexford
    -0.72
     Uttar
    -0.70
    canza
    -0.69
     يتيمه
    -0.68
     Yag
    -0.68
     FSC
    -0.65
    USC
    -0.63
    </h1>
    -0.63
    stdbool
    -0.63
    POSITIVE LOGITS
     THAN
    1.00
    Than
    0.84
     Than
    0.79
    THAN
    0.78
     the
    0.77
     than
    0.74
     EconPapers
    0.69
    zzleHttp
    0.65
     gainera
    0.65
    OrEqualTo
    0.64
    Act Density 0.112%

    No Known Activations