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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.40
    rachtet
    -0.36
    jaciół
    -0.35
    A
    -0.35
    ThroughAttribute
    -0.35
     qued
    -0.32
     faltan
    -0.31
    waża
    -0.30
     Handwerk
    -0.30
     cuadros
    -0.30
    POSITIVE LOGITS
     beſch
    0.81
    AddTagHelper
    0.80
     verſch
    0.78
     geſch
    0.78
     Waſſer
    0.77
     zwiſchen
    0.77
    ſcher
    0.76
    parsedMessage
    0.76
    wiſe
    0.76
     ſes
    0.75
    Act Density 0.026%

    No Known Activations