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

    Neuronpedia

    INDEX
    Explanations

    words related to emotions and feelings, particularly focusing on mood

    oai_token-act-pair · gpt-3.5-turbo

    references to various moods and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ded
    -0.67
    ces
    -0.66
     Universities
    -0.65
    ichen
    -0.64
    pta
    -0.64
    adr
    -0.63
     Prosecut
    -0.63
    chnology
    -0.62
    ced
    -0.61
    xton
    -0.61
    POSITIVE LOGITS
     mood
    1.05
     Mood
    0.87
    y
    0.80
     swings
    0.79
    iness
    0.75
    achine
    0.75
     conducive
    0.72
     Indigo
    0.72
    spection
    0.71
    atically
    0.71
    Act Density 0.023%

    No Known Activations