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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.86
     itſelf
    -0.84
     houſe
    -0.82
     hierogly
    -0.75
     Sega
    -0.74
     pleaſure
    -0.74
     ſche
    -0.73
     Majefty
    -0.73
     Anſ
    -0.70
    ſelf
    -0.69
    POSITIVE LOGITS
     the
    1.11
     it
    0.74
    "])
    0.73
     if
    0.72
     there
    0.72
     “
    0.72
    :\/\/
    0.66
     some
    0.66
     WaitForSeconds
    0.65
    )")
    0.65
    Act Density 0.364%

    No Known Activations