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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and quantifying expressions referring to groups or quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantity or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mobil
    -0.70
     expanding
    -0.67
     Mobil
    -0.66
     underway
    -0.65
     Farming
    -0.63
    moil
    -0.63
    hern
    -0.63
    APS
    -0.63
    forth
    -0.62
    osher
    -0.61
    POSITIVE LOGITS
     guy
    1.18
     times
    1.05
     guys
    1.04
     people
    1.00
    body
    0.98
     dude
    0.95
     dudes
    0.95
     reviewers
    0.92
     folks
    0.91
     thing
    0.90
    Act Density 0.473%

    No Known Activations