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

    Neuronpedia

    INDEX
    Explanations

    questions containing the word "asked"

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns in the context of questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nowhere
    -0.69
     Species
    -0.64
     PCR
    -0.61
    WithNo
    -0.60
    olulu
    -0.59
     Brunswick
    -0.58
     Mechanics
    -0.58
     ROS
    -0.58
     Written
    -0.57
     obscurity
    -0.57
    POSITIVE LOGITS
     regretted
    1.26
     ever
    1.21
     bothered
    1.11
     thought
    1.07
    'd
    1.06
     knew
    1.02
     minded
    1.02
     felt
    1.01
     would
    1.00
     wished
    0.99
    Act Density 0.142%

    No Known Activations