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

    Neuronpedia

    INDEX
    Explanations

    references to the Oxford University or its associated entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    lli
    -0.71
    moder
    -0.70
     Kran
    -0.65
     NIM
    -0.62
    🔥🔥
    -0.60
     ê
    -0.59
    ilet
    -0.58
    Ile
    -0.58
     بيها
    -0.58
     י
    -0.57
    POSITIVE LOGITS
     Oxford
    1.57
    Oxford
    1.51
     OXFORD
    1.40
     oxford
    1.38
    oxford
    1.09
     Oxfordshire
    0.96
     trouw
    0.93
     '\\;'
    0.89
     OX
    0.84
     nakalista
    0.81
    Act Density 0.002%

    No Known Activations