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

    Neuronpedia

    INDEX
    Explanations

    expressions related to emotional states and experiences

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

    emotional states, experiences, or burdens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.75
     CascadeType
    -0.59
     nahilalakip
    -0.53
     mijne
    -0.53
    InputBorder
    -0.52
     hipótesis
    -0.51
    +#+#
    -0.51
     Nacionales
    -0.50
     daß
    -0.50
     exemplu
    -0.50
    POSITIVE LOGITS
     Emotion
    0.81
    emotional
    0.81
     Emo
    0.80
    Emotional
    0.80
     Emotional
    0.79
    Emotion
    0.75
    Emotions
    0.75
    Emo
    0.74
     Emotions
    0.71
     emotional
    0.71
    Act Density 0.006%

    No Known Activations