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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by emotional states

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to individuals and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reach
    -0.77
    athon
    -0.76
    clave
    -0.70
    ML
    -0.68
    shed
    -0.68
    eligible
    -0.68
    ielding
    -0.68
    mire
    -0.67
    grid
    -0.67
    gain
    -0.66
    POSITIVE LOGITS
     Majesty
    1.02
     tides
    0.81
    mos
    0.75
     majesty
    0.74
     salty
    0.73
     charms
    0.70
     fuckin
    0.70
    illac
    0.69
     Vaj
    0.69
    folk
    0.68
    Act Density 0.485%

    No Known Activations