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

    Neuronpedia

    INDEX
    Explanations

    references to software or systems used in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rop
    -0.49
    ird
    -0.48
    ger
    -0.47
    ting
    -0.47
     disguise
    -0.46
    ifolia
    -0.46
     gauge
    -0.46
    ner
    -0.46
    enstein
    -0.46
    ley
    -0.45
    POSITIVE LOGITS
     Monfieur
    0.79
     auffi
    0.77
     leaſt
    0.65
     pérd
    0.63
     ſon
    0.62
     faſt
    0.62
     juſ
    0.61
     indígen
    0.61
    wiſe
    0.61
     ſta
    0.60
    Act Density 0.212%

    No Known Activations