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

    Neuronpedia

    INDEX
    Explanations

    the repeated phrase "those" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.68
    ChildScrollView
    -0.62
     Monter
    -0.58
    tse
    -0.57
     Micah
    -0.55
     betweenstory
    -0.55
    waffe
    -0.55
    éroport
    -0.55
    sune
    -0.54
    kedés
    -0.54
    POSITIVE LOGITS
     those
    4.23
    those
    3.75
    Those
    3.69
     Those
    3.55
     THOSE
    3.13
     aqueles
    2.54
     ceux
    2.51
     aquellos
    2.44
    那些
    2.31
    queles
    2.22
    Act Density 0.080%

    No Known Activations