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

    Neuronpedia

    INDEX
    Explanations

    specific sentences containing the word "that"

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tank
    -0.77
    ress
    -0.74
    pee
    -0.68
    ãĥīãĥ©
    -0.65
    ãĥĺ
    -0.64
    kat
    -0.64
     gasp
    -0.63
    roo
    -0.62
     discard
    -0.61
    Ò
    -0.61
    POSITIVE LOGITS
     "[
    0.87
     "...
    0.72
     although
    0.71
     "âĢ¦
    0.69
     "#
    0.69
    imates
    0.66
    .):
    0.62
     '[
    0.62
     "(
    0.62
    terday
    0.61
    Act Density 0.187%

    No Known Activations