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

    Neuronpedia

    INDEX
    Explanations

    sentences with subject-verb agreements and actions taken by collective subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     my
    -0.37
    GenerationType
    -0.37
     myself
    -0.35
     me
    -0.33
    是个
    -0.33
    larımız
    -0.32
     என
    -0.32
     víctima
    -0.32
     والذي
    -0.32
    是個
    -0.31
    POSITIVE LOGITS
     themselves
    1.22
    Their
    1.16
    their
    1.14
    themselves
    1.13
     their
    1.09
     Their
    1.05
     loro
    1.02
     mereka
    0.98
     they
    0.97
    他們的
    0.97
    Act Density 1.311%

    No Known Activations