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

    Neuronpedia

    INDEX
    Explanations

    The neuron is looking for phrases starting with "That"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "that" and related phrases indicating explanation or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rhodes
    -0.69
     Liberty
    -0.68
     Pegasus
    -0.65
     CNS
    -0.63
     Newark
    -0.62
     Compass
    -0.61
     Kad
    -0.60
     Myster
    -0.59
     Forth
    -0.59
     JFK
    -0.59
    POSITIVE LOGITS
    âĢ
    2.04
     âĢ
    1.37
    âĶ
    1.36
    >>>>
    1.31
    ¨
    1.30
    âĸł
    1.29
    ãĢ
    1.28
    «
    1.28
    Ò
    1.25
    ÃĥÃĤ
    1.23
    Act Density 0.242%

    No Known Activations