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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to personal pronouns and collective identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forth
    -0.83
     NEO
    -0.81
     DOS
    -0.77
     Nelson
    -0.75
     Liberty
    -0.75
     JFK
    -0.73
     monopoly
    -0.73
     Essex
    -0.73
     Kissinger
    -0.73
     Speedway
    -0.72
    POSITIVE LOGITS
    âĢ
    1.53
    ´
    1.07
    ÃĥÃĤ
    0.99
    ñ
    0.94
    Í
    0.92
    he
    0.91
    hl
    0.90
    ÃĥÃĤÃĥÃĤ
    0.89
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    0.89
    cffffcc
    0.89
    Act Density 0.176%

    No Known Activations