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

    Neuronpedia

    INDEX
    Explanations

    the word "which" and variations of it

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
      (
    -0.72
    enumi
    -0.67
    oas
    -0.66
     Kyr
    -0.65
     Jefus
    -0.63
     DMs
    -0.62
     
    -0.61
    ograma
    -0.60
     Anm
    -0.60
    ABO
    -0.60
    POSITIVE LOGITS
     např
    0.64
     whilst
    0.63
     ISNI
    0.62
     enquiries
    0.58
     realising
    0.57
     Enquiries
    0.57
    олові
    0.56
    Nuorodos
    0.56
    faßt
    0.56
     ouvriers
    0.56
    Act Density 0.084%

    No Known Activations