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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.46
    __(/*!
    -0.39
    adaptiveStyles
    -0.38
    Rüyada
    -0.37
    recated
    -0.36
    لينكات
    -0.36
    erto
    -0.35
     cli
    -0.35
    Slf
    -0.35
    /*
    -0.35
    POSITIVE LOGITS
     That
    1.52
     THAT
    1.45
    That
    1.45
     those
    1.41
    THAT
    1.28
    Those
    1.25
     Those
    1.24
    those
    1.23
     THOSE
    1.23
     daquele
    1.13
    Act Density 0.246%

    No Known Activations