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

    Neuronpedia

    INDEX
    Explanations

    spatial relationships and locations within a descriptive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -has
    -0.17
     hadn
    -0.15
    \Has
    -0.14
     HAS
    -0.14
    (has
    -0.14
    ’Ñıз
    -0.14
     Didn
    -0.14
    didn
    -0.14
    .Has
    -0.13
    _HAS
    -0.13
    POSITIVE LOGITS
     are
    0.42
    çļĦæĺ¯
    0.33
     is
    0.29
     there
    0.29
     were
    0.25
     estão
    0.24
     lies
    0.23
    _are
    0.23
     ÙĩستÙĨد
    0.22
     theres
    0.22
    Act Density 0.186%

    No Known Activations