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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "Have you ever" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    questions about personal experiences or reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Annex
    -0.70
    Alright
    -0.63
     specificity
    -0.59
     Definitions
    -0.59
    urity
    -0.59
     ABV
    -0.59
    ources
    -0.58
    humans
    -0.58
    Okay
    -0.58
     endorsements
    -0.58
    POSITIVE LOGITS
     wondered
    1.43
     fantas
    1.16
     overheard
    1.15
     wished
    1.13
     heard
    1.11
     regretted
    1.08
     pond
    1.07
     contemplated
    1.06
     wonder
    1.06
     glanced
    1.04
    Act Density 0.223%

    No Known Activations