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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recent updates or new information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     JSTOR
    -0.65
     отношению
    -0.63
     sẻ
    -0.63
    muo
    -0.61
    Kalb
    -0.60
     uParam
    -0.59
     RMS
    -0.59
    Goa
    -0.58
     Cubs
    -0.58
     Balboa
    -0.57
    POSITIVE LOGITS
     latest
    1.62
     LATEST
    1.57
    Latest
    1.50
    LATEST
    1.48
     Latest
    1.48
    latest
    1.47
     newest
    1.27
     最新
    1.19
     neuesten
    1.13
    newest
    1.12
    Act Density 0.029%

    No Known Activations