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

    Neuronpedia

    INDEX
    Explanations

    emotional reactions and responses in contexts involving conflict or challenge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baseURL
    -0.46
     present
    -0.45
    сылкі
    -0.45
    AnimationFrame
    -0.45
     provided
    -0.43
    TestingModule
    -0.42
    cmu
    -0.41
     past
    -0.41
     schia
    -0.41
     "
    -0.40
    POSITIVE LOGITS
     arouse
    0.92
     aroused
    0.88
     alarmed
    0.87
     offended
    0.86
     offend
    0.83
     attract
    0.83
     attracted
    0.81
     attracts
    0.81
     Irrit
    0.79
     applause
    0.78
    Act Density 0.193%

    No Known Activations