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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ambro
    -0.65
    ãĥ³ãĤ¸
    -0.65
     Dimension
    -0.61
    Contents
    -0.61
    interstitial
    -0.60
     Rosenthal
    -0.60
     Sabha
    -0.58
    dimension
    -0.57
     Gw
    -0.57
    Balt
    -0.57
    POSITIVE LOGITS
    're
    1.30
     wanna
    1.06
     want
    1.01
    've
    1.01
     guessed
    0.99
     wish
    0.90
     guys
    0.90
     hear
    0.84
     decide
    0.84
     subscribe
    0.84
    Act Density 0.085%

    No Known Activations