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

    Neuronpedia

    INDEX
    Explanations

    the word "those" and its variations, indicating a focus on specific groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wilber
    -0.88
     MEG
    -0.76
    Nag
    -0.75
    ocarp
    -0.74
     Bertram
    -0.73
    AnchorStyles
    -0.73
     Puig
    -0.73
     écou
    -0.72
    lename
    -0.72
    laps
    -0.71
    POSITIVE LOGITS
     those
    1.61
    those
    1.37
    Those
    1.34
     Those
    1.30
     THOSE
    1.19
     ceux
    1.04
     aquellos
    1.04
     who
    1.01
     aqueles
    0.98
     celles
    0.93
    Act Density 0.092%

    No Known Activations