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

    Neuronpedia

    INDEX
    Explanations

    concepts and references related to harmony and unity

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

    harmony and harmonious states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Deadpool
    -0.52
     Scrooge
    -0.43
     Deadpool
    -0.43
     didst
    -0.40
     extir
    -0.40
    <![
    -0.40
    Jeb
    -0.40
     sigui
    -0.40
    expandindo
    -0.39
     Jeb
    -0.39
    POSITIVE LOGITS
     Harmony
    2.23
    Harmony
    2.13
     harmony
    2.13
    harmony
    1.97
     armonía
    1.54
     harmonie
    1.50
     harmonies
    1.48
     harmonious
    1.47
     Harmonie
    1.46
     Harmon
    1.36
    Act Density 0.002%

    No Known Activations