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

    Neuronpedia

    INDEX
    Explanations

    references to numeric values or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typelib
    -0.73
    GEBURTSDATUM
    -0.60
    Autoritní
    -0.60
    PreferredItem
    -0.57
     Bars
    -0.56
     vPvB
    -0.56
     Cram
    -0.54
     useAppContext
    -0.54
     ala
    -0.53
     paras
    -0.53
    POSITIVE LOGITS
     mesmas
    0.64
     avoient
    0.61
     étoient
    0.58
     mismas
    0.57
     dezelve
    0.56
     étoit
    0.54
     financeiro
    0.53
     mêmes
    0.50
     intermédiaire
    0.48
     desmotivaciones
    0.47
    Act Density 0.109%

    No Known Activations