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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.46
    InstrumentedTest
    -0.46
     оригіналу
    -0.41
     Passer
    -0.41
     Mate
    -0.39
    xfc
    -0.39
    AVIA
    -0.39
    makedirs
    -0.38
    ÕES
    -0.38
     lad
    -0.38
    POSITIVE LOGITS
     Obrador
    0.71
    WithIOException
    0.62
    󠁣
    0.55
    lusconi
    0.50
    phosa
    0.49
     mergeFrom
    0.49
     Chomsky
    0.49
     Gorbachev
    0.49
     Wikimedijinoj
    0.48
    celotti
    0.47
    Act Density 0.799%

    No Known Activations