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

    Neuronpedia

    INDEX
    Explanations

    references to NATO and Putin in the text

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.56
     Irak
    -0.54
    {}".
    -0.53
     POM
    -0.52
     grunn
    -0.51
    enste
    -0.50
    SharedCtor
    -0.50
     griego
    -0.49
     fapt
    -0.49
     Kerk
    -0.49
    POSITIVE LOGITS
     MLS
    0.96
     NATO
    0.93
    MetaObject
    0.92
    ophysical
    0.85
     puck
    0.84
    eline
    0.81
     PGA
    0.80
     plo
    0.79
    kovsky
    0.79
     Cytometry
    0.78
    Act Density 0.050%

    No Known Activations