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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.56
    fjspx
    -0.56
     CreateTagHelper
    -0.56
     webdriver
    -0.56
    GenerationType
    -0.53
     SRT
    -0.53
     smtplib
    -0.52
     Erdoğan
    -0.50
    Beverly
    -0.50
    OutputType
    -0.50
    POSITIVE LOGITS
     glad
    0.69
     cesse
    0.65
    didSet
    0.64
    etheless
    0.63
    jalá
    0.61
     Glad
    0.61
    spół
    0.61
     Fridge
    0.60
     frein
    0.60
    glad
    0.58
    Act Density 0.157%

    No Known Activations