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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal structure and historical inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    textAlignment
    -0.52
     Lookout
    -0.50
     houdt
    -0.48
     Cæsar
    -0.48
     devoirs
    -0.47
     []:
    -0.46
     dianteiro
    -0.44
     vọng
    -0.44
     Wib
    -0.44
     poveznice
    -0.44
    POSITIVE LOGITS
    RegistryLite
    0.99
     would
    0.96
    ########.
    0.95
    would
    0.91
    Would
    0.86
    Personendaten
    0.85
     Would
    0.84
     WOULD
    0.84
     للمعارف
    0.82
     насељу
    0.78
    Act Density 0.393%

    No Known Activations