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

    Neuronpedia

    INDEX
    Explanations

    words related to intelligence and capability

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.87
     nahilalakip
    -0.86
     Gough
    -0.84
    hedrals
    -0.83
     InputDecoration
    -0.81
    FileDescriptor
    -0.81
    DebuggerNonUser
    -0.80
    Geplaatst
    -0.79
    LabelTagHelper
    -0.79
    IsContent
    -0.78
    POSITIVE LOGITS
     Smart
    1.21
     smart
    1.14
    Smart
    1.10
     SMART
    1.09
     intelligent
    1.07
     inteligente
    1.06
     Intelligent
    1.05
    smar
    1.05
     intelligence
    1.05
    smart
    1.02
    Act Density 0.095%

    No Known Activations