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

    Neuronpedia

    INDEX
    Explanations

    terms related to negative emotions and states of distress

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

    attributed to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lucas
    -0.52
     somethin
    -0.47
     Primo
    -0.46
    Guns
    -0.45
     Linus
    -0.44
     lieutenant
    -0.44
    Lieutenant
    -0.43
     Ruger
    -0.43
    CIF
    -0.43
    Numer
    -0.43
    POSITIVE LOGITS
     despair
    1.70
     Despair
    1.51
     betweenstory
    0.88
    绝望
    0.76
     desesper
    0.73
     anguish
    0.70
     desolation
    0.70
     HasFactory
    0.69
     sorrow
    0.68
     OFDb
    0.67
    Act Density 0.002%

    No Known Activations