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

    Neuronpedia

    INDEX
    Explanations

    phrases regarding human actions and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.16
    ama
    -0.14
    Äįast
    -0.14
    ãģ¤ãģ¶
    -0.14
     ÑĤебÑı
    -0.13
    ssp
    -0.13
     senin
    -0.13
    ãĢĤä½ł
    -0.13
     ÑĤебе
    -0.13
     hạ
    -0.13
    POSITIVE LOGITS
     Mr
    1.35
    Mr
    1.19
     Ms
    0.97
     mr
    0.90
     Mrs
    0.81
    Ms
    0.79
    mr
    0.68
    _mr
    0.68
     MR
    0.66
    Mrs
    0.66
    Act Density 0.366%

    No Known Activations