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

    Neuronpedia

    INDEX
    Explanations

    proper names and specific terms related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.86
     Rios
    -0.72
     Horton
    -0.70
     Rü
    -0.70
    te
    -0.69
     tinh
    -0.68
    HOS
    -0.68
     Fairy
    -0.67
    (";
    -0.67
     Ava
    -0.67
    POSITIVE LOGITS
     Crowe
    0.96
     Galapagos
    0.83
     crocs
    0.82
     oprot
    0.81
    XmlAccessorType
    0.80
     commis
    0.80
     habet
    0.79
    Salva
    0.78
     Rooney
    0.78
     Embal
    0.77
    Act Density 1.751%

    No Known Activations