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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conversational elements and personal interactions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     engraçado
    -0.77
     Paglinawan
    -0.76
     Kingfisher
    -0.71
     Mademoiselle
    -0.70
    useState
    -0.68
     frau
    -0.67
     Krug
    -0.67
     subsidence
    -0.67
     Cæsar
    -0.66
     onData
    -0.66
    POSITIVE LOGITS
    |}{\
    0.62
    Hogyan
    0.59
     Tar
    0.58
    LEGGI
    0.58
     got
    0.57
     εξ
    0.57
    ORIAL
    0.57
    ecin
    0.57
    efit
    0.56
    ceiro
    0.56
    Act Density 0.024%

    No Known Activations