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

    Neuronpedia

    INDEX
    Explanations

    personal experiences and emotional reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to personal experiences and opinions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Whilst
    -0.70
    azard
    -0.61
    untled
    -0.60
    Detailed
    -0.60
    Introduction
    -0.59
     controvers
    -0.59
     Shroud
    -0.59
    Dispatch
    -0.58
    Firstly
    -0.57
     Contribut
    -0.56
    POSITIVE LOGITS
    laughs
    1.13
     fuckin
    1.10
     gonna
    1.02
    laugh
    0.96
     gotta
    0.92
    Laughs
    0.90
     wanna
    0.87
     somet
    0.85
     tho
    0.84
     kidding
    0.82
    Act Density 1.159%

    No Known Activations