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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by questions or statements expressing doubt, uncertainty, or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating personal involvement or address in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.75
    ãĤ¦ãĤ¹
    -0.72
    ãĥĵ
    -0.70
    uces
    -0.70
     Giul
    -0.66
     srfAttach
    -0.66
     Conversation
    -0.65
     Integrity
    -0.64
    ufact
    -0.64
    opens
    -0.64
    POSITIVE LOGITS
     deserve
    1.09
     intend
    1.08
     recognise
    1.01
     lose
    0.99
     need
    0.99
     propose
    0.97
     owe
    0.97
     think
    0.95
     mean
    0.95
     expect
    0.95
    Act Density 0.079%

    No Known Activations