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

    Neuronpedia

    INDEX
    Explanations

    terms related to suffering and distress in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gefe
    -0.43
     cheeky
    -0.39
     soap
    -0.37
     Wedge
    -0.36
     slate
    -0.36
    Доб
    -0.36
     bross
    -0.35
    alsch
    -0.35
     plan
    -0.35
     domine
    -0.35
    POSITIVE LOGITS
     propOrder
    0.85
    تقاوى
    0.61
     bezeichneter
    0.58
     defaultstate
    0.58
    principalColumn
    0.57
     تضيفلها
    0.56
    findpost
    0.53
    Losses
    0.52
     suffer
    0.51
     losses
    0.51
    Act Density 0.137%

    No Known Activations