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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social actions and support efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.15
    eview
    -0.15
    queen
    -0.14
     ÑĤебÑı
    -0.14
    èĪĹ
    -0.14
    اÙħا
    -0.14
    inceton
    -0.13
     queen
    -0.13
    maid
    -0.13
    allee
    -0.13
    POSITIVE LOGITS
     Mr
    1.41
    Mr
    1.27
     mr
    0.98
     Ms
    0.89
    mr
    0.81
     Mrs
    0.78
     MR
    0.76
    _mr
    0.74
     Mister
    0.74
    Ms
    0.71
    Act Density 0.712%

    No Known Activations