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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" and its frequency of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     punishing
    -0.73
     weakening
    -0.69
     reminding
    -0.69
    cffffcc
    -0.69
     lowering
    -0.67
    ãĥĥ
    -0.67
     distracting
    -0.64
     inhib
    -0.64
     aiming
    -0.63
     curing
    -0.62
    POSITIVE LOGITS
     comprise
    1.20
     participated
    1.16
     preceded
    1.16
     survived
    1.12
     emerged
    1.01
     perished
    1.01
     entered
    1.01
     compose
    1.01
     mattered
    1.00
     came
    0.98
    Act Density 0.162%

    No Known Activations