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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дописавши
    -0.83
    Personendaten
    -0.81
    Jîn
    -0.64
    NameInMap
    -0.63
    Erreferentziak
    -0.57
    omock
    -0.55
    Vidite
    -0.55
    Geplaatst
    -0.55
     AppModule
    -0.54
    pogon
    -0.52
    POSITIVE LOGITS
     again
    0.86
    ditto
    0.78
     also
    0.78
     likewise
    0.75
    同上
    0.73
    again
    0.70
     επίσης
    0.69
     ditto
    0.68
     similarly
    0.67
     idem
    0.64
    Act Density 0.785%

    No Known Activations