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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſind
    -0.69
     noOf
    -0.60
    BIM
    -0.59
     Piles
    -0.57
     Carni
    -0.57
     iſt
    -0.56
    LookAnd
    -0.55
     Silverstone
    -0.55
     Sensi
    -0.55
     PVP
    -0.54
    POSITIVE LOGITS
     That
    1.20
    That
    1.20
     THAT
    1.12
    THAT
    1.02
    that
    0.96
     that
    0.92
    那
    0.72
    Those
    0.71
     THOSE
    0.70
    quela
    0.69
    Act Density 0.291%

    No Known Activations