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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "that"

    np_acts-logits-general · gemini-2.0-flash

    that followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.96
     Shakspeare
    -0.88
     Efq
    -0.83
     Pelop
    -0.81
     Majefty
    -0.80
     ddelweddau
    -0.78
     Cæsar
    -0.77
     Houſe
    -0.76
     alfo
    -0.75
     ་་
    -0.75
    POSITIVE LOGITS
     the
    1.29
     there
    1.28
     it
    1.25
     we
    1.08
     this
    1.06
     they
    1.06
     although
    0.97
     if
    0.94
     he
    0.91
     you
    0.90
    Act Density 0.370%

    No Known Activations