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

    Neuronpedia

    INDEX
    Explanations

    expressions of doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.62
    HtmlAttribute
    -0.60
    RRect
    -0.59
     fortunately
    -0.58
     AssemblyCompany
    -0.58
     pleaſure
    -0.57
     signé
    -0.56
     <<<<<<<<<<<<<<
    -0.56
     thankfully
    -0.56
     luckily
    -0.56
    POSITIVE LOGITS
     something
    0.92
    Something
    0.82
    something
    0.80
     Something
    0.77
     disambiguazione
    0.73
    何か
    0.70
     somehow
    0.70
     valami
    0.68
     quelque
    0.66
     somewhere
    0.65
    Act Density 0.383%

    No Known Activations