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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive determiners indicating ownership or attribution

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and verbs related to expressing support or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amazon
    -0.76
    £ı
    -0.72
     resembling
    -0.70
    athon
    -0.69
     spawned
    -0.66
     Canaver
    -0.65
    phan
    -0.65
     Pwr
    -0.65
     akin
    -0.64
    tch
    -0.64
    POSITIVE LOGITS
     displeasure
    1.40
     disapproval
    1.27
     own
    1.26
     condolences
    1.19
     thoughts
    1.17
     frustrations
    1.10
     gratitude
    1.08
     opinion
    1.07
     grievances
    1.05
     intentions
    1.05
    Act Density 0.151%

    No Known Activations