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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures or groups that hold significant influence or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lenker
    -0.62
    EndGlobalSection
    -0.49
    Personendaten
    -0.46
    Slf
    -0.44
     kasarigan
    -0.43
     насељу
    -0.41
    الإنجليزية
    -0.41
     ProtoMessage
    -0.41
    čiau
    -0.41
     commento
    -0.40
    POSITIVE LOGITS
     humble
    0.49
     semplici
    0.47
    simple
    0.47
     simple
    0.47
     little
    0.46
     dusty
    0.46
     poignée
    0.45
    little
    0.44
     tiny
    0.43
    dusty
    0.43
    Act Density 0.408%

    No Known Activations