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

    Neuronpedia

    INDEX
    Explanations

    pronouns and personal reflections

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and the word "it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     monopoly
    -0.75
     Airbnb
    -0.63
     bureaucracy
    -0.62
     disk
    -0.60
     Ventura
    -0.60
     Disneyland
    -0.59
     firm
    -0.59
     machine
    -0.58
     Dropbox
    -0.58
     textbook
    -0.58
    POSITIVE LOGITS
    âĢ
    1.19
    «
    1.11
    ´
    1.06
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.06
    ^
    1.05
    ÃĥÃĤÃĥÃĤ
    1.04
    *
    1.02
    **
    1.01
    `
    0.98
    Â
    0.97
    Act Density 0.267%

    No Known Activations