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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors and terms associated with social or political criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.67
     فريبيس
    -0.65
    yntaxException
    -0.62
    Хьажоргаш
    -0.54
     Superhost
    -0.52
    IVEREF
    -0.51
    httphttps
    -0.51
     للاسماء
    -0.51
    matchCondition
    -0.49
    SPATH
    -0.48
    POSITIVE LOGITS
     lixo
    0.53
     waste
    0.50
     inutile
    0.49
     stupid
    0.48
     basura
    0.47
     Stupid
    0.43
    stupid
    0.42
     pointless
    0.42
     useless
    0.42
    waste
    0.41
    Act Density 0.644%

    No Known Activations