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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical military funding and armaments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Allows
    -0.70
    #$
    -0.69
    .","
    -0.68
    ãĥĺ
    -0.66
    dk
    -0.66
    rade
    -0.65
    Ò
    -0.65
    ãĥ»
    -0.64
    ""
    -0.63
    âĵĺ
    -0.63
    POSITIVE LOGITS
    resa
    1.41
    odore
    1.41
    oret
    1.41
     Problem
    1.29
     downside
    1.23
    ories
    1.19
     irony
    1.19
     gist
    1.18
     Basics
    1.17
     problem
    1.10
    Act Density 0.370%

    No Known Activations