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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omitempty
    -0.57
     technically
    -0.52
    uzzi
    -0.49
     bumi
    -0.48
    ExecutorService
    -0.48
    CppMethod
    -0.46
    смотреть
    -0.46
    EXPECT
    -0.44
    يديا
    -0.44
    routeProvider
    -0.44
    POSITIVE LOGITS
     that
    0.94
    that
    0.89
     που
    0.75
     jotka
    0.72
     které
    0.71
     Whose
    0.71
     Whom
    0.69
    which
    0.69
     које
    0.69
     whom
    0.69
    Act Density 0.263%

    No Known Activations