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

    Neuronpedia

    INDEX
    Explanations

    instances where the text discusses plans, announcements, or updates on projects and events

    oai_token-act-pair · gpt-3.5-turbo

    affirmative statements of various emotional qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     restraint
    -0.73
    âĢ¢âĢ¢
    -0.69
    SPONSORED
    -0.67
     fails
    -0.67
    othal
    -0.66
    Shape
    -0.66
     preced
    -0.65
    ["
    -0.64
     lasts
    -0.64
    APD
    -0.64
    POSITIVE LOGITS
     pleased
    1.20
     delighted
    1.12
     thrilled
    1.11
     proud
    1.07
     glad
    1.04
     currently
    0.99
     hoping
    0.98
     excited
    0.97
     collaborating
    0.96
     thankful
    0.95
    Act Density 0.182%

    No Known Activations