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

    Neuronpedia

    INDEX
    Explanations

    opinions or beliefs expressed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to people's opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clad
    -0.75
    ague
    -0.68
     clad
    -0.64
    iona
    -0.64
     Adin
    -0.63
    çĦ
    -0.62
    eding
    -0.62
    ORPG
    -0.61
    conservancy
    -0.61
     Peninsula
    -0.61
    POSITIVE LOGITS
     provoking
    0.78
     aloud
    0.75
     differently
    0.72
    ij士
    0.70
    ileaks
    0.68
     about
    0.68
    IUM
    0.65
    ventus
    0.65
     alike
    0.65
     wrongly
    0.64
    Act Density 0.075%

    No Known Activations