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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by the verb 'to have.'

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to personal and group identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majority
    -0.70
     Sapp
    -0.68
     Dunk
    -0.66
     Globe
    -0.65
     Agg
    -0.65
    luster
    -0.62
     Lobby
    -0.61
     Hau
    -0.61
     Bundes
    -0.60
     Gutenberg
    -0.59
    POSITIVE LOGITS
    athed
    1.06
    've
    1.00
    RL
    0.99
    uristic
    0.97
     hadn
    0.97
     deems
    0.95
    'd
    0.94
     deem
    0.92
     couldn
    0.91
    arers
    0.86
    Act Density 0.144%

    No Known Activations