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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments related to experiences, particularly in service and food reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ainfi
    -0.85
     enfans
    -0.72
     nôtre
    -0.69
     vieilles
    -0.68
     varandra
    -0.67
     allmän
    -0.67
     nemlig
    -0.65
     titolata
    -0.65
     hunne
    -0.64
     conseguenza
    -0.64
    POSITIVE LOGITS
     =
    0.69
     noqa
    0.60
     +
    0.60
     plus
    0.59
     disambiguazione
    0.59
     autorytatywna
    0.59
     незавершена
    0.58
    责任编辑
    0.58
     no
    0.56
     OK
    0.55
    Act Density 0.627%

    No Known Activations