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

    Neuronpedia

    INDEX
    Explanations

    the word "those" and its variations, particularly in the context of grouping or referencing individuals or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayne
    -0.17
    enberg
    -0.14
    EventArgs
    -0.14
     gratuito
    -0.14
    serie
    -0.14
    strt
    -0.14
    erner
    -0.14
    arshal
    -0.14
    enos
    -0.14
    unya
    -0.14
    POSITIVE LOGITS
     who
    0.38
    who
    0.28
     whose
    0.25
     whom
    0.23
     qui
    0.19
     اÙĦØ°ÙĬÙĨ
    0.19
     Who
    0.19
    Who
    0.18
    whose
    0.18
     kteÅĻÃŃ
    0.17
    Act Density 0.042%

    No Known Activations