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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flavors
    -0.17
    favor
    -0.17
     rumor
    -0.15
     traveled
    -0.15
     Favor
    -0.15
    avior
    -0.15
     centers
    -0.15
    –
    -0.15
    ̣
    -0.15
     favor
    -0.14
    POSITIVE LOGITS
     Bahamas
    0.25
     Bah
    0.21
    Bah
    0.18
     Christie
    0.17
     electricity
    0.15
     Tribune
    0.15
     Government
    0.15
     Cabinet
    0.15
     Caribbean
    0.15
    bah
    0.14
    Act Density 0.000%

    No Known Activations