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

    Neuronpedia

    INDEX
    Explanations

    quotes by people attributed with 'said that'

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" used as a conjunction or a connector in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.74
    EMBER
    -0.61
    backer
    -0.61
    ien
    -0.60
    gur
    -0.58
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.55
    Occup
    -0.54
    oses
    -0.54
    Guard
    -0.54
    arest
    -0.54
    POSITIVE LOGITS
    cher
    0.77
     "#
    0.75
     although
    0.70
     "[
    0.69
     sounded
    0.67
     they
    0.67
     contradicts
    0.66
    esson
    0.66
     '[
    0.62
    ebus
    0.62
    Act Density 0.329%

    No Known Activations