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

    Neuronpedia

    INDEX
    Explanations

    common first-person pronouns and phrases indicating personal action or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.05
     itſelf
    -1.05
     Efq
    -1.04
    IVEREF
    -1.00
    StoryboardSegue
    -0.98
     pleaſure
    -0.95
    GEBURTSDATUM
    -0.94
     Shakspeare
    -0.94
     greateſt
    -0.94
     fubject
    -0.94
    POSITIVE LOGITS
    *}\
    0.65
     use
    0.60
     far
    0.53
    [])
    0.51
     a
    0.50
     carefully
    0.49
    نس
    0.49
     using
    0.49
    ).\
    0.49
     previously
    0.48
    Act Density 0.552%

    No Known Activations