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

    Neuronpedia

    INDEX
    Explanations

    the word "that" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùĩ
    -0.20
    ãģĤãĤĬ
    -0.19
    s
    -0.18
    amp
    -0.17
    ãģĤãĤĭ
    -0.17
    ÏĤ
    -0.16
    ised
    -0.15
    ãģĤãģ£ãģŁ
    -0.15
    ive
    -0.14
    sans
    -0.14
    POSITIVE LOGITS
     particular
    0.35
    ched
    0.32
    /th
    0.31
    zelf
    0.28
     same
    0.27
    ching
    0.23
     exact
    0.22
     PARTICULAR
    0.21
    cher
    0.21
     же
    0.20
    Act Density 0.130%

    No Known Activations